
import os
import math
import random
import numpy as np
import polars as pl
import seaborn as sns
import xgboost as xgb
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = [20, 5]
plt.rcParams["figure.autolayout"] = True
pl.Config.set_tbl_rows(256)

import nmf.nmf as nmf
import knee.kneedle as kneedle

from sklearn.cluster import KMeans
from sklearn.pipeline import Pipeline
from sklearn.mixture import GaussianMixture

from sklearn.svm import SVR
from sklearn.neural_network import MLPRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.linear_model import LinearRegression, Lasso
from sklearn.ensemble import GradientBoostingRegressor, RandomForestRegressor

from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
from sklearn.model_selection import StratifiedKFold, GridSearchCV
from sklearn.preprocessing import StandardScaler, OneHotEncoder

# Remove SciKit Learn warnings
import warnings
warnings.filterwarnings('ignore')
os.environ["PYTHONWARNINGS"] = "ignore" # Also affect subprocesses


df = pl.read_excel('db.xlsx')
df = df.drop(['#'])
df


sns.pairplot(df.to_pandas())
fig = plt.gcf()
fig.savefig(f'figures/pairplot.pdf', bbox_inches='tight')
plt.show()


sns.pairplot(df.to_pandas(), hue='PCE (%)')
plt.show()


sns.pairplot(df.to_pandas(), hue='hopt (%)')
plt.show()


def idx_to_rowcol(idx, width):
    r = int(idx / width)
    c = int(idx % width)
    return (r,c)


def rowcol_to_idx(r,c, width):
    idx = int((r * width) + c)
    return idx


def describe_variables(df, categorical=['mat0', 'mat1'], cols=4, figsize=(20,15), filename=None):
    # get the pandas dataframe (since polars does not allow plots)
    df_pandas = df.to_pandas()
    for col in categorical:
        df_pandas[col] = df_pandas[col].astype('category')
    
    # compute the number of rows
    total = (2 * len(df.get_columns())) - len(categorical)
    rows = math.ceil(total/cols)
    fig, axes = plt.subplots(rows, cols, constrained_layout = True, figsize=figsize)
    #print(f'Total {total} -> ({rows} {cols})')
    
    idx = 0
    for col in df.get_columns():
        r, c = idx_to_rowcol(idx, cols)
        #print(f'({col.name}: {idx} -> {r}, {c})')
        sns.histplot(ax=axes[r, c], data=df_pandas, x=col.name)
        idx += 1
        if col.name not in categorical:
            r, c = idx_to_rowcol(idx, cols)
            #print(f'({col.name}: {idx} -> {r}, {c})')
            sns.boxplot(ax=axes[r, c], data=df_pandas, x=col.name)
            idx += 1
    if isinstance(filename, str):
        fig = plt.gcf()
        fig.savefig(f'figures/{filename}.pdf', bbox_inches='tight')
    plt.show()


describe_variables(df, filename='feaures_description')


def print_missing_samples(df):
    print(f'Shape: {df.shape}')
    total, _ = df.shape
    for col in df.get_columns():
        print(f'{col.name:<6}: {col.is_null().sum()/total:.0%}')


print_missing_samples(df)

Shape: (201, 11)
mat0  : 0%
mat1  : 0%
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 14%
hopt (%): 28%
PCE (%): 36%


df_baseline_PCE = df.drop(['mat0', 'mat1', 'QY (%)', 'hopt (%)']).drop_nulls()
print_missing_samples(df_baseline_PCE)

Shape: (128, 7)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
PCE (%): 0%


df_baseline_hopt = df.drop(['mat0', 'mat1', 'QY (%)', 'PCE (%)']).drop_nulls()
print_missing_samples(df_baseline_hopt)

Shape: (144, 7)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
hopt (%): 0%


max_depth = [int(x) for x in np.linspace(10, 100, num = 5)]
max_depth.append(None)

# TODO: fix this
# Print Models parameters
models = [('Linear Regression', LinearRegression(), {}),
          ('K Neighbors', KNeighborsRegressor(),
           {'reg__n_neighbors':[1,3,5,7,9], 'reg__weights':['uniform', 'distance'], 'reg__p':[1,2]}),
          ('Random Forest', RandomForestRegressor(random_state=42),
           {'reg__n_estimators':[50, 100, 150, 200], 'reg__min_samples_split':[2, 5, 10],
            'reg__min_samples_leaf':[1, 2, 4], 'reg__bootstrap':[True, False], 'reg__max_depth':max_depth}),
          ('Gradient Boosting', GradientBoostingRegressor(random_state=42),
           {'reg__n_estimators':[50, 100, 150, 200],'reg__min_samples_split':[2, 5, 10],
            'reg__min_samples_leaf':[1, 2, 4], 'reg__max_depth':max_depth}),
         ('XGBoost', xgb.XGBRegressor(objective="reg:squarederror", random_state=42),
          {'reg__max_depth': range (2, 10, 1), 'reg__n_estimators': range(60, 220, 40), 'reg__learning_rate': [0.1, 0.01, 0.05]})]

# remove heavy models that do not perform that well
#('Lasso Regression', Lasso(max_iter=5000, tol=1E-2, random_state=42), {'alpha': (np.logspace(-8, 8, 20))}),
#('Support Vector Regressor', SVR(),{'C': [0.1, 1, 10, 100], 'gamma': [1, 0.1, 0.01],'kernel': ['linear','rbf', 'sigmoid']}),
#('ANN', MLPRegressor(max_iter=50000,  tol=1E-3, random_state=42),{'hidden_layer_sizes':[(8,), (16,), (32,)],'activation':['relu','logistic'], 'learning_rate':['constant', 'invscaling', 'adaptive']}),


def create_folds(X, y, b='auto', k=5):
    if isinstance(b, str):
        bins = np.histogram_bin_edges(y, bins=b)
        # remove the last index (end point)
        bins = bins[:-1]
    elif isinstance(b, int):
        bins = np.linspace(min(y), max(y), num=b, endpoint=False)
    else:
        raise Exception(f'Undefined bins {b}')
        
    #print(f'Bins: {bins}')
    groups = np.digitize(y, bins)
    #print(f'Group: {groups}')
    skf = StratifiedKFold(n_splits=k)
    return skf.split(X, groups)


from collections.abc import Iterable

def compute_performance(models, X, y, b=None, k=[5, 3], filename=None):
    if isinstance(k, Iterable):
        outer_k = k[0]
        inner_k = k[1]
    elif isinstance(k, int):
        outer_k = k
        inner_k = k
    else:
        raise Exception(f'Undefined k {k}')

    #kf = KFold(n_splits=cv)
    folds = create_folds(X, y, b=b, k=outer_k)
    
    perf_per_model = {}
    y_true = []
    y_true_train = []
    y_preds = {}
    y_preds_train = {}
    #for train_index, test_index in kf.split(X):
    for train_index, test_index in folds:
        X_train, X_test, y_train, y_test = X[train_index], X[test_index], y[train_index], y[test_index]
    
        y_true.extend(y_test)
        y_true_train.extend(y_train)
    
        # optimize each model and store the best result
        best_models = []
        for _, model, params in models:
            pipeline = Pipeline([('sca', StandardScaler()),('reg', model)])
            #clf = GridSearchCV(pipeline, params, cv=cv, scoring='neg_mean_absolute_error', n_jobs=-1)
            grid_folds = create_folds(X_train, y_train, b=b, k=inner_k)
            #clf = GridSearchCV(pipeline, params, cv=cv, scoring='r2', n_jobs=-1)
            clf = GridSearchCV(pipeline, params, cv=grid_folds, scoring='r2', n_jobs=-1)
            clf.fit(X_train, y_train)
            best_models.append(clf.best_estimator_)

        # compute the predictions and store the results
        for i in range(len(models)):
            model = best_models[i]
            y_pred = model.predict(X_test)
            y_pred_train = model.predict(X_train)
            
            if models[i][0] not in y_preds:
                y_preds[models[i][0]] = []
            
            if models[i][0] not in y_preds_train:
                y_preds_train[models[i][0]] = []
            
            y_preds[models[i][0]].extend(y_pred)
            y_preds_train[models[i][0]].extend(y_pred_train)
            
            score_mae_test = mean_absolute_error(y_test, y_pred)
            score_mse_test = mean_squared_error(y_test, y_pred)
            score_r2_test = r2_score(y_test, y_pred)
            
            score_mae_train = mean_absolute_error(y_train, y_pred_train)
            score_mse_train = mean_squared_error(y_train, y_pred_train)
            score_r2_train = r2_score(y_train, y_pred_train)
            
            if models[i][0] not in perf_per_model:
                perf_per_model[models[i][0]] = {'train':{'mae':[], 'mse': [], 'r2':[]},
                                                'test':{'mae':[], 'mse': [], 'r2':[]}}
            
            perf_per_model[models[i][0]]['test']['mae'].append(score_mae_test)
            perf_per_model[models[i][0]]['test']['mse'].append(score_mse_test)
            perf_per_model[models[i][0]]['test']['r2'].append(score_r2_test)
            
            perf_per_model[models[i][0]]['train']['mae'].append(score_mae_train)
            perf_per_model[models[i][0]]['train']['mse'].append(score_mse_train)
            perf_per_model[models[i][0]]['train']['r2'].append(score_r2_train)
            
    # print the results
    print(f'Train')
    print(f'| {"Model":^17} | {"MAE":^6} | {"MSE":^6} | {"R2":^6} |')
    print(f'| ----------------- | ------ | ------ | ------ |')
    for i in range(len(models)):
        mae = perf_per_model[models[i][0]]['train']['mae']
        mse = perf_per_model[models[i][0]]['train']['mse']
        r2  = perf_per_model[models[i][0]]['train']['r2']
        #print(f'{mae} | {mse} | {r2}')
        mae = np.mean(mae)
        mse = np.mean(mse)
        r2  = np.mean(r2)
        print(f'| {models[i][0]:<17} | {round(mae, 2):>6} | {round(mse, 2):>6} | {round(r2, 2):>6} |')
    print()
    
    print(f'Test')
    print(f'| {"Model":^17} | {"MAE":^6} | {"MSE":^6} | {"R2":^6} |')
    print(f'| ----------------- | ------ | ------ | ------ |')
    for i in range(len(models)):
        mae = perf_per_model[models[i][0]]['test']['mae']
        mse = perf_per_model[models[i][0]]['test']['mse']
        r2  = perf_per_model[models[i][0]]['test']['r2']
        #print(f'{mae} | {mse} | {r2}')
        mae = np.mean(mae)
        mse = np.mean(mse)
        r2  = np.mean(r2)
        print(f'| {models[i][0]:<17} | {round(mae, 2):>6} | {round(mse, 2):>6} | {round(r2, 2):>6} |')
    print()

    # plot the graphs
    print(f'Train')
    data_train = []
    labels_train = []
    for name, _, _ in models:
        labels_train.append(name)

        # DEBUG STUFF:
        #score_mae = mean_absolute_error(y_true_train, y_preds_train[name])
        #score_mse = mean_squared_error(y_true_train, y_preds_train[name])
        #score_r2 = r2_score(y_true_train, y_preds_train[name])
        #print(f'Model {name} {score_mae} {score_mse} {score_r2}')

        data_train.append(np.abs(np.subtract(y_true_train, y_preds_train[name])))
    ax = sns.violinplot(data=data_train)
    ax.set_xticklabels(labels_train)
    if isinstance(filename, str):
        fig = plt.gcf()
        fig.savefig(f'figures/{filename}_train.pdf', bbox_inches='tight')
    plt.show()

    print(f'Test')
    data_preds = []
    labels_preds = []
    for name, _, _ in models:
        labels_preds.append(name)

        # DEBUG STUFF:
        #score_mae = mean_absolute_error(y_true, y_preds[name])
        #score_mse = mean_squared_error(y_true, y_preds[name])
        #score_r2 = r2_score(y_true, y_preds[name])
        #print(f'Model {name} {score_mae} {score_mse} {score_r2}')

        data_preds.append(np.abs(np.subtract(y_true, y_preds[name])))
    ax = sns.violinplot(data=data_preds)
    ax.set_xticklabels(labels_preds)
    if isinstance(filename, str):
        fig = plt.gcf()
        fig.savefig(f'figures/{filename}_test.pdf', bbox_inches='tight')
    plt.show()
    
    # convert best_models to a dict and return it
    bm = {}
    for name, model, params in models:
        # train on whole dataset
        pipeline = Pipeline([('sca', StandardScaler()),('reg', model)])
        #clf = GridSearchCV(pipeline, params, cv=cv, scoring='neg_mean_absolute_error', n_jobs=-1)
        grid_folds = create_folds(X, y, b=b, k=inner_k)
        clf = GridSearchCV(pipeline, params, cv=grid_folds, scoring='r2', n_jobs=-1)
        clf.fit(X, y)
        bm[name] = clf.best_estimator_
    
    return bm


# Get Output variables
PCE = df_baseline_PCE[['PCE (%)']]
y_PCE = PCE.to_numpy()[:,0]
#print(f'{y_PCE} {y_PCE.shape}')

# Get the Input variables
df_input = df_baseline_PCE.drop(['PCE (%)'])
X = df_input.to_numpy()
#print(f'{X} {X.shape}')

## PCE
print(f'PCE')
models_pce_baseline = compute_performance(models, X, y_PCE, b='auto', k=[9, 3], filename='pce_baseline')

PCE
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.53 |   4.39 |   0.13 |
| K Neighbors       |   0.22 |   0.46 |   0.91 |
| Random Forest     |   0.85 |   1.95 |   0.61 |
| Gradient Boosting |   0.25 |   0.26 |   0.95 |
| XGBoost           |   0.76 |   1.56 |   0.69 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.66 |   5.15 |  -0.01 |
| K Neighbors       |   1.31 |    4.1 |    0.2 |
| Random Forest     |   1.28 |   4.04 |   0.25 |
| Gradient Boosting |    1.3 |   4.42 |   0.16 |
| XGBoost           |   1.32 |   4.26 |    0.2 |

Train

Test


# Get Output variables
hopt = df_baseline_hopt[['hopt (%)']]
y_hopt = hopt.to_numpy()[:,0]

# Get the Input variables
df_input = df_baseline_hopt.drop(['hopt (%)'])
X = df_input.to_numpy()

## hopt
print(f'hopt')
models_hopt_baseline = compute_performance(models, X, y_hopt, b='auto', k=[9, 3], filename='hopt_baseline')

hopt
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   5.14 |  65.18 |   0.07 |
| K Neighbors       |   0.98 |   8.88 |   0.87 |
| Random Forest     |   3.09 |  28.37 |    0.6 |
| Gradient Boosting |   1.13 |   4.37 |   0.94 |
| XGBoost           |   3.82 |  49.78 |    0.3 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   5.71 |  75.71 |  -0.15 |
| K Neighbors       |   4.69 |  62.34 |  -0.05 |
| Random Forest     |   5.19 |  68.62 |  -0.12 |
| Gradient Boosting |   4.76 |  67.24 |  -0.28 |
| XGBoost           |   4.54 |  66.16 |   0.02 |

Train

Test


df_02_PCE = df.drop(['mat0', 'mat1', 'hopt (%)']).drop_nulls()
print_missing_samples(df_02_PCE)

Shape: (112, 8)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
PCE (%): 0%


df_02_hopt = df.drop(['mat0', 'mat1', 'PCE (%)']).drop_nulls()
print_missing_samples(df_02_hopt)

Shape: (129, 8)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
hopt (%): 0%


# Get Output variables
PCE = df_02_PCE[['PCE (%)']]
y_PCE = PCE.to_numpy()[:,0]

# Get the Input variables
df_input = df_02_PCE.drop(['PCE (%)'])
X = df_input.to_numpy()

## PCE
print(f'PCE')
models_02_pce = compute_performance(models, X, y_PCE, b='auto', k=[9, 3], filename='pce_qy')

PCE
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.48 |   4.21 |   0.13 |
| K Neighbors       |   0.12 |   0.15 |   0.97 |
| Random Forest     |   0.78 |   1.78 |   0.63 |
| Gradient Boosting |   0.26 |   0.28 |   0.94 |
| XGBoost           |   1.01 |   2.76 |   0.42 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.64 |   4.99 |  -0.17 |
| K Neighbors       |   1.11 |    3.8 |   0.17 |
| Random Forest     |   1.32 |   4.37 |  -0.23 |
| Gradient Boosting |   1.44 |   5.48 |  -0.64 |
| XGBoost           |   1.43 |   5.41 |  -0.32 |

Train

Test


# Get Output variables
hopt = df_02_hopt[['hopt (%)']]
y_hopt = hopt.to_numpy()[:,0]

# Get the Input variables
df_input = df_02_hopt.drop(['hopt (%)'])
X = df_input.to_numpy()

## hopt
print(f'hopt')
models_02_hopt = compute_performance(models, X, y_hopt, b='auto', k=[9, 3], filename='hopt_qy')

hopt
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   5.25 |  62.42 |   0.18 |
| K Neighbors       |   2.38 |  23.96 |   0.68 |
| Random Forest     |   3.43 |  36.95 |   0.52 |
| Gradient Boosting |    0.8 |   3.32 |   0.95 |
| XGBoost           |   3.37 |  37.93 |   0.51 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   5.86 |  73.91 |  -0.39 |
| K Neighbors       |   4.56 |  50.99 |  -0.01 |
| Random Forest     |   4.97 |  64.28 |  -0.26 |
| Gradient Boosting |   4.95 |  70.14 |  -0.62 |
| XGBoost           |   4.21 |   63.4 |  -0.04 |

Train

Test


df_03_PCE = df.drop(['hopt (%)']).drop_nulls()
print_missing_samples(df_03_PCE)

Shape: (112, 10)
mat0  : 0%
mat1  : 0%
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
PCE (%): 0%


df_03_hopt = df.drop(['PCE (%)']).drop_nulls()
print_missing_samples(df_03_hopt)

Shape: (129, 10)
mat0  : 0%
mat1  : 0%
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
hopt (%): 0%


# Get Output variables
PCE = df_03_PCE[['PCE (%)']]
y_PCE = PCE.to_numpy()[:,0]

# Get the Input variables
df_input = df_03_PCE.drop(['mat0', 'mat1', 'PCE (%)'])
X = df_input.to_numpy()

temp_mat0 = df_03_PCE[['mat0']].to_numpy()
enc = OneHotEncoder(min_frequency=10, sparse_output=False)
encoded_mat0 = enc.fit_transform(temp_mat0)

temp_mat1 = df_03_PCE[['mat1']].to_numpy()
enc = OneHotEncoder(min_frequency=20, sparse_output=False)
encoded_mat1 = enc.fit_transform(temp_mat1)

X = np.concatenate((encoded_mat0, encoded_mat1, X), axis=1)

## PCE
print(f'PCE')
models_03_pce = compute_performance(models, X, y_PCE, b='auto', k=[9, 3], filename='pce_qy_mat')

PCE
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.17 |   3.16 |   0.34 |
| K Neighbors       |   0.12 |   0.15 |   0.97 |
| Random Forest     |   0.79 |   1.82 |   0.62 |
| Gradient Boosting |   0.27 |   0.28 |   0.94 |
| XGBoost           |   1.01 |   2.77 |   0.42 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.44 |   4.72 |  -0.34 |
| K Neighbors       |    1.1 |   4.02 |   0.03 |
| Random Forest     |    1.3 |   4.35 |   -0.2 |
| Gradient Boosting |   1.29 |   5.35 |  -0.53 |
| XGBoost           |   1.38 |   4.91 |  -0.11 |

Train

Test


# Get Output variables
hopt = df_03_hopt[['hopt (%)']]
y_hopt = hopt.to_numpy()[:,0]

# Get the Input variables
df_input = df_03_hopt.drop(['mat0', 'mat1', 'hopt (%)'])
X = df_input.to_numpy()

temp_mat0 = df_03_hopt[['mat0']].to_numpy()
enc = OneHotEncoder(min_frequency=10, sparse_output=False)
encoded_mat0 = enc.fit_transform(temp_mat0)

temp_mat1 = df_03_hopt[['mat1']].to_numpy()
enc = OneHotEncoder(min_frequency=20, sparse_output=False)
encoded_mat1 = enc.fit_transform(temp_mat1)

X = np.concatenate((encoded_mat0, encoded_mat1, X), axis=1)

## hopt
print(f'hopt')
models_03_hopt = compute_performance(models, X, y_hopt, b='auto', k=[9, 3], filename='hopt_qy_mat')

hopt
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   4.71 |  47.33 |   0.38 |
| K Neighbors       |   0.99 |   9.13 |   0.89 |
| Random Forest     |   2.27 |  17.14 |   0.78 |
| Gradient Boosting |   0.49 |   1.48 |   0.98 |
| XGBoost           |   2.04 |  11.67 |   0.85 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   5.62 |  64.31 |  -0.26 |
| K Neighbors       |   4.12 |  47.73 |   0.15 |
| Random Forest     |   4.06 |  43.72 |   0.19 |
| Gradient Boosting |   4.52 |  60.79 |  -0.07 |
| XGBoost           |   3.67 |  40.66 |    0.3 |

Train

Test


def iqr_range(array):
    Q1 = np.percentile(array, 25)
    Q3 = np.percentile(array, 75)
    IQR = Q3 - Q1
    return ((Q1 - 1.5 * IQR),(Q3 + 1.5 * IQR))


PCE_array = df[['PCE (%)']].drop_nulls().to_numpy()[:,0]
#PCE_array
pce_low, pce_high = iqr_range(PCE_array)
print(f'PCE [{pce_low}, {pce_high}]')

PCE [-4.000000000000001, 6.912000000000001]


df_filtered_PCE = df.filter((pl.col('PCE (%)') > pce_low) & (pl.col('PCE (%)') < pce_high))
sns.boxplot(data=df_filtered_PCE.to_pandas(), x='PCE (%)')
plt.show()
print(f'PCE: {df_filtered_PCE.shape}')

PCE: (121, 11)


hopt_array = df[['hopt (%)']].drop_nulls().to_numpy()[:,0]
#hopt_array
hopt_low, hopt_high = iqr_range(hopt_array)
print(f'hopt [{hopt_low}, {hopt_high}]')

hopt [-6.99875, 15.63125]


df_filtered_hopt = df.filter((pl.col('hopt (%)') > pce_low) & (pl.col('hopt (%)') < pce_high))
sns.boxplot(data=df_filtered_hopt.to_pandas(), x='hopt (%)')
plt.show()
print(f'nhop: {df_filtered_hopt.shape}')

nhop: (106, 11)


#models_gbr = [('Gradient Boosting Regressor', GradientBoostingRegressor(random_state=42),
#{'n_estimators':[50, 100, 150],'min_samples_split':[2, 5, 10], 'min_samples_leaf':[1, 2, 4],'max_depth':max_depth})]


df_out_baseline_PCE = df_filtered_PCE.drop(['mat0', 'mat1', 'QY (%)', 'hopt (%)']).drop_nulls()
print_missing_samples(df_out_baseline_PCE)

Shape: (121, 7)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
PCE (%): 0%


# Get Output variables
PCE = df_out_baseline_PCE[['PCE (%)']]
y_PCE = PCE.to_numpy()[:,0]

# Get the Input variables
df_input = df_out_baseline_PCE.drop(['PCE (%)'])
X = df_input.to_numpy()

## PCE
print(f'PCE')
models_out_pce_baseline = compute_performance(models, X, y_PCE, b='auto', k=[9, 3], filename='pce_nout_baseline')

PCE
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.15 |    2.0 |   0.14 |
| K Neighbors       |   0.26 |   0.39 |   0.83 |
| Random Forest     |   0.45 |   0.46 |    0.8 |
| Gradient Boosting |   0.17 |   0.15 |   0.93 |
| XGBoost           |   0.54 |   0.69 |    0.7 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.25 |   2.35 |  -0.01 |
| K Neighbors       |   0.99 |   1.94 |    0.1 |
| Random Forest     |   0.91 |   1.62 |   0.25 |
| Gradient Boosting |   0.79 |   1.53 |   0.28 |
| XGBoost           |   1.05 |   2.08 |   0.03 |

Train

Test


df_out_baseline_hopt = df_filtered_hopt.drop(['mat0', 'mat1', 'QY (%)', 'PCE (%)']).drop_nulls()
print_missing_samples(df_out_baseline_hopt)

Shape: (106, 7)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
hopt (%): 0%


# Get Output variables
hopt = df_out_baseline_hopt[['hopt (%)']]
y_hopt = hopt.to_numpy()[:,0]

# Get the Input variables
df_input = df_out_baseline_hopt.drop(['hopt (%)'])
X = df_input.to_numpy()

## hopt
print(f'hopt')
models_out_hopt_baseline = compute_performance(models, X, y_hopt, b='auto', k=[9, 3], filename='hopt_nout_baseline')

hopt
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.43 |   3.11 |   0.04 |
| K Neighbors       |    0.1 |   0.09 |   0.97 |
| Random Forest     |   0.85 |   1.11 |   0.66 |
| Gradient Boosting |   0.32 |   0.22 |   0.93 |
| XGBoost           |   1.07 |   1.76 |   0.46 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.59 |   3.86 |  -0.18 |
| K Neighbors       |   1.36 |   2.88 |   0.09 |
| Random Forest     |   1.44 |   3.04 |   0.04 |
| Gradient Boosting |    1.5 |   3.39 |  -0.06 |
| XGBoost           |   1.45 |   3.18 |   0.01 |

Train

Test


df_out_02_PCE = df_filtered_PCE.drop(['mat0', 'mat1', 'hopt (%)']).drop_nulls()
print_missing_samples(df_out_02_PCE)

Shape: (107, 8)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
PCE (%): 0%


df_out_02_hopt = df_filtered_hopt.drop(['mat0', 'mat1', 'PCE (%)']).drop_nulls()
print_missing_samples(df_out_02_hopt)

Shape: (95, 8)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
hopt (%): 0%


# Get Output variables
PCE = df_out_02_PCE[['PCE (%)']]
y_PCE = PCE.to_numpy()[:,0]

# Get the Input variables
df_input = df_out_02_PCE.drop(['PCE (%)'])
X = df_input.to_numpy()

## PCE
print(f'PCE')
models_out_02_pce = compute_performance(models, X, y_PCE, b='auto', k=[9, 3], filename='pce_nout_qy')

PCE
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.11 |   1.91 |   0.12 |
| K Neighbors       |   0.12 |   0.14 |   0.93 |
| Random Forest     |   0.39 |   0.37 |   0.83 |
| Gradient Boosting |   0.16 |   0.16 |   0.93 |
| XGBoost           |   0.56 |   0.71 |   0.67 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.27 |   2.42 |  -0.15 |
| K Neighbors       |   0.99 |   1.97 |   0.11 |
| Random Forest     |   0.91 |   1.65 |   0.24 |
| Gradient Boosting |   0.96 |   2.03 |   0.05 |
| XGBoost           |   0.97 |   1.85 |   0.15 |

Train

Test


# Get Output variables
hopt = df_out_02_hopt[['hopt (%)']]
y_hopt = hopt.to_numpy()[:,0]

# Get the Input variables
df_input = df_out_02_hopt.drop(['hopt (%)'])
X = df_input.to_numpy()

## hopt
print(f'hopt')
models_out_02_hopt = compute_performance(models, X, y_hopt, b='auto', k=[9, 3], filename='hopt_nout_qy')

hopt
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.45 |   3.18 |   0.04 |
| K Neighbors       |   0.48 |   0.87 |   0.74 |
| Random Forest     |   0.66 |   0.74 |   0.78 |
| Gradient Boosting |   0.21 |   0.13 |   0.96 |
| XGBoost           |   0.97 |   1.52 |   0.54 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.63 |   4.12 |   -0.3 |
| K Neighbors       |   1.36 |   2.91 |   0.07 |
| Random Forest     |    1.4 |   2.92 |   0.07 |
| Gradient Boosting |   1.47 |   3.55 |  -0.14 |
| XGBoost           |   1.42 |   3.15 |   0.01 |

Train

Test


df_out_03_PCE = df_filtered_PCE.drop(['hopt (%)']).drop_nulls()
print_missing_samples(df_out_03_PCE)

Shape: (107, 10)
mat0  : 0%
mat1  : 0%
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
PCE (%): 0%


df_out_03_hopt = df_filtered_hopt.drop(['PCE (%)']).drop_nulls()
print_missing_samples(df_out_03_hopt)

Shape: (95, 10)
mat0  : 0%
mat1  : 0%
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%
hopt (%): 0%


# Get Output variables
PCE = df_out_03_PCE[['PCE (%)']]
y_PCE = PCE.to_numpy()[:,0]

# Get the Input variables
df_input = df_out_03_PCE.drop(['mat0', 'mat1', 'PCE (%)'])
X = df_input.to_numpy()

temp_mat0 = df_out_03_PCE[['mat0']].to_numpy()
enc = OneHotEncoder(min_frequency=10, sparse_output=False)
encoded_mat0 = enc.fit_transform(temp_mat0)

temp_mat1 = df_out_03_PCE[['mat1']].to_numpy()
enc = OneHotEncoder(min_frequency=20, sparse_output=False)
encoded_mat1 = enc.fit_transform(temp_mat1)

X = np.concatenate((encoded_mat0, encoded_mat1, X), axis=1)

## PCE
print(f'PCE')
models_out_03_pce = compute_performance(models, X, y_PCE, b='auto', k=[9, 3], filename='pce_nout_qy_mat')

PCE
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   0.79 |   1.15 |   0.47 |
| K Neighbors       |   0.17 |   0.21 |    0.9 |
| Random Forest     |   0.35 |    0.3 |   0.86 |
| Gradient Boosting |   0.14 |   0.15 |   0.93 |
| XGBoost           |    0.4 |   0.45 |   0.79 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.02 |    1.8 |   0.16 |
| K Neighbors       |   0.88 |   1.72 |   0.22 |
| Random Forest     |   0.88 |   1.56 |   0.28 |
| Gradient Boosting |   0.96 |   1.99 |   0.06 |
| XGBoost           |    1.0 |   2.16 |  -0.02 |

Train

Test


# Get Output variables
hopt = df_out_03_hopt[['hopt (%)']]
y_hopt = hopt.to_numpy()[:,0]

# Get the Input variables
df_input = df_out_03_hopt.drop(['mat0', 'mat1', 'hopt (%)'])
X = df_input.to_numpy()

temp_mat0 = df_out_03_hopt[['mat0']].to_numpy()
enc = OneHotEncoder(min_frequency=10, sparse_output=False)
encoded_mat0 = enc.fit_transform(temp_mat0)

temp_mat1 = df_out_03_hopt[['mat1']].to_numpy()
enc = OneHotEncoder(min_frequency=20, sparse_output=False)
encoded_mat1 = enc.fit_transform(temp_mat1)

X = np.concatenate((encoded_mat0, encoded_mat1, X), axis=1)

## PCE
print(f'hopt')
models_out_03_hopt = compute_performance(models, X, y_hopt, b='auto', k=[9, 3], filename='hopt_nout_qy_mat')

hopt
Train
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.36 |   2.84 |   0.14 |
| K Neighbors       |   0.21 |   0.36 |   0.89 |
| Random Forest     |   0.63 |   0.64 |   0.81 |
| Gradient Boosting |   0.18 |   0.11 |   0.97 |
| XGBoost           |   0.97 |   1.53 |   0.54 |

Test
|       Model       |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Linear Regression |   1.71 |   4.66 |  -0.48 |
| K Neighbors       |    1.4 |   3.05 |   0.06 |
| Random Forest     |   1.41 |   3.02 |   0.04 |
| Gradient Boosting |   1.49 |    3.6 |  -0.12 |
| XGBoost           |   1.43 |   3.28 |  -0.04 |

Train

Test


df = pl.read_excel('db.xlsx')
#df = df.drop(['#'])
df_clustering_index = df.drop(['mat0', 'mat1', 'hopt (%)', 'PCE (%)'])
df_clustering_index = df_clustering_index.drop_nulls()
df_clustering = df_clustering_index.drop(['#'])
print_missing_samples(df_clustering)

Shape: (173, 7)
abs_peak: 0%
abs_min: 0%
abs_max: 0%
em_peak: 0%
em_min: 0%
em_max: 0%
QY (%): 0%


import sklearn.metrics as sklearn_metrics

def inertia_score(X, labels):
  """This is the same of scikit-learn's KMeans.inertia_, but it works also in case of only one label."""

  inertia = 0.0
  for label in set(labels):
    X_cluster = X[labels == label, :]
    centroid = np.mean(X_cluster, axis=0)
    inertia += np.sum((X_cluster - centroid) ** 2)
  return inertia


def calinski_harabasz_score(X, labels):
  """Wrapper function of Scikit-learn's calinski_harabasz_score. The only difference is it doesn't throw an error where there is only one label."""
  
  if len(set(labels)) == 1:
    return float("NaN")
  else:
    return sklearn_metrics.calinski_harabasz_score(X, labels)


def davies_bouldin_score(X, labels):
  """Wrapper function of Scikit-learn's davies_bouldin_score. The only difference is it doesn't throw an error where there is only one label."""
  
  if len(set(labels)) == 1:
    return float("NaN")
  else:
    return sklearn_metrics.davies_bouldin_score(X, labels)


def silhouette_score(X, labels):
  """Wrapper function of Scikit-learn's silhouette_score. The only difference is it doesn't throw an error where there is only one label."""
  
  if len(set(labels)) == 1:
    return float("NaN")
  else:
    return sklearn_metrics.silhouette_score(X, labels)


def get_bic_aic(k, X):
    gmm = GaussianMixture(n_components=k, init_params='kmeans')
    gmm.fit(X)
    return gmm.bic(X), gmm.aic(X)


# Cluster the materials without the hopt and PCE
X = df_clustering.to_numpy()
print(f'X = {X.shape}')

scores = {'elbow': [], 'calinski-harabasz': [], 'davies-bouldin': [], 'silhouette': [], 'bic': [], }

min_k = 2
max_k = 20

for k in range(min_k, max_k):
    kmeans = KMeans(n_clusters=k, max_iter=1000, n_init='auto', init='k-means++', random_state=5).fit(X)
    labels = kmeans.labels_
    scores['elbow'].append(inertia_score(X, labels))
    scores['calinski-harabasz'].append(calinski_harabasz_score(X, labels))
    scores['davies-bouldin'].append(davies_bouldin_score(X, labels))
    scores['silhouette'].append(silhouette_score(X, labels))
    bic, _ = get_bic_aic(k, X)
    scores['bic'].append(bic)

X = (173, 7)


x = range(min_k, max_k)
y = scores['elbow']

points = np.zeros((len(y),2))
points[:,0] = x
points[:,1] = y


methods = ['elbow', 'calinski-harabasz', 'davies-bouldin', 'silhouette', 'bic']
fig, axs = plt.subplots(1, 5)

for i in range(len(methods)):
    method = methods[i]
    
    axs[i].plot(range(min_k, max_k), scores[method])
    if method == 'elbow':
        idx = kneedle.auto_knee(points)
    elif method == 'calinski-harabasz':
        idx = scores[method].index(max(scores[method]))
        #axs[i].plot(x[idx], scores[method][idx], 'ro')
    elif method == 'davies-bouldin':
        idx = scores[method].index(min(scores[method]))
        #axs[i].plot(x[idx], scores[method][idx], 'ro')
    elif method == 'silhouette':
        idx = scores[method].index(max(scores[method]))
        #axs[i].plot(x[idx], scores[method][idx], 'ro')
    elif method == 'bic':
        idx = scores[method].index(max(scores[method]))
        #axs[i].plot(x[idx], scores[method][idx], 'ro')
    axs[i].plot(x[idx], scores[method][idx], 'ro')
fig = plt.gcf()
fig.savefig(f'figures/kmeans.pdf', bbox_inches='tight')
plt.show()


def compute_avg_field_per_cluster(df_origin, df_clustering, labels, field='PCE (%)'):
    field_per_cluster = []
    min_k = min(labels)
    max_k = max(labels)
    #print(f'[{min_k}, {max_k}]')
    for k in range(min_k, max_k+1):
        mask = (labels == k)
        #print(f'k={k} = {mask} {mask.shape} {df.shape}')
        df_k = df_clustering.filter(mask)
        #print(f'{df_k}')
        cluster_labels = df_k['#'].to_list()
        #print(f'{cluster_labels}')
        filter_df = df_origin.filter(pl.col('#').is_in(cluster_labels))
        #print(filter_df)
        mean_field = filter_df[field].mean()
        field_per_cluster.append(mean_field)
    return field_per_cluster

def plot_stats_per_cluster(df_origin, df_clustering, labels):
    min_k = min(labels)
    max_k = max(labels)
    #print(f'[{min_k}, {max_k}]')
    for k in range(min_k, max_k+1):
        print(f'Cluster: {k}')
        mask = (labels == k)
        #print(f'k={k} = {mask} {mask.shape} {df.shape}')
        df_k = df_clustering.filter(mask)
        #print(f'{df_k}')
        cluster_labels = df_k['#'].to_list()
        #print(f'{cluster_labels}')
        filter_df = df_origin.filter(pl.col('#').is_in(cluster_labels))
        describe_variables(filter_df.drop(['#']), filename=f'cluster_{k}')

def find_nearest(array, value):
    diff = np.sum(np.abs(array - value), axis=1)
    idx = diff.argmin()
    return idx

def find_nearest_df(df, df_origin, value, k, field):
    df_no_id = df.drop(['#'])
    array = df_no_id.to_numpy()
    diff = np.sum(np.abs(array - value), axis=1)
    idxs = []
    
    i = j = 0
    while i < k and j < len(diff):
        j += 1
        idx = diff.argmin()
        #print(f'Current idx {idx}')
        diff[idx] = float('inf')
        #print(f'{df_origin.row(idx, named=True)}')
        if df_origin.row(idx, named=True)[field] is not None:
            idxs.append(idx)
            i += 1
    
    idxs = [df.row(i, named=True)['#'] for i in idxs]
    return idxs

def get_missing(df, field):
    df_qy_not_null = df.filter(pl.col('QY (%)').is_not_null())
    missing_df = df_qy_not_null.filter(pl.col(field).is_null())
    missing = missing_df.drop(['#', 'mat0', 'mat1', 'hopt (%)', 'PCE (%)']).to_numpy()
    return missing
    #return missing_df
    #vector_df = missing_df.drop(['#', 'mat0', 'mat1', 'hopt (%)', 'PCE (%)'])
    #missing = vector_df.to_numpy()

def predict_field_clustering(df_origin, df_clustering, kmeans, k=3, field='PCE (%)'):
    labels = kmeans.labels_
    centroids  = kmeans.cluster_centers_
    #centroid_labels = [centroids[i] for i in labels]
    #print(f'{labels} {centroids}')
    
    missing = get_missing(df_origin, field)
    #missing = missing_df.drop(['#', 'mat0', 'mat1', 'hopt (%)', 'PCE (%)']).to_numpy()

    # for each missing point, find the closest cluster
    rv = []
    for row in missing:
        closest_cluster = find_nearest(centroids, row)
        # select the corresponding cluster
        mask = (labels == closest_cluster)
        df_k = df_clustering.filter(mask)
        temp_id = df_k['#'].to_list()
        df_origin_k = df_origin.filter(pl.col('#').is_in(temp_id))
        idxs = find_nearest_df(df_k, df_origin_k, row, k, field)
        filter_df = df_origin.filter(pl.col('#').is_in(idxs))
        # compute the average
        pce_k = filter_df[field].to_numpy()
        rv.append((np.mean(pce_k), np.median(pce_k)))
    return rv

def get_clusters_df(df_origin, df_clustering, labels):
    min_k = min(labels)
    max_k = max(labels)

    df_per_cluster = []

    for k in range(min_k, max_k+1):
        mask = (labels == k)
        #print(f'k={k} = {mask} {mask.shape} {df.shape}')
        df_k = df_clustering.filter(mask)
        #print(f'{df_k}')
        cluster_labels = df_k['#'].to_list()
        #print(f'{cluster_labels}')
        filter_df = df_origin.filter(pl.col('#').is_in(cluster_labels))
        #print(filter_df)
        #mean_field = filter_df[field].mean()
        #field_per_cluster.append(mean_field)
        df_per_cluster.append(filter_df)
    return df_per_cluster


def rmse(measured, truth):
    return np.linalg.norm(measured - truth) / np.sqrt(len(truth))


k=5
kmeans = KMeans(n_clusters=k, max_iter=1000, n_init='auto', init='k-means++', random_state=5).fit(X)
labels = kmeans.labels_


avg_pce_cluster = compute_avg_field_per_cluster(df, df_clustering_index, labels, field='PCE (%)')
print(f'Avg PCE cluster: {avg_pce_cluster}')
avg_hopt_cluster = compute_avg_field_per_cluster(df, df_clustering_index, labels, field='hopt (%)')
print(f'Avg hOPT cluster: {avg_hopt_cluster}')
predictions_pce = predict_field_clustering(df, df_clustering_index, kmeans, k=3, field='PCE (%)')
print(f'Predictions PCE: {predictions_pce}')
predictions_hopt = predict_field_clustering(df, df_clustering_index, kmeans, k=3, field='hopt (%)')
print(f'Predictions hOPT: {predictions_hopt}')

Avg PCE cluster: [1.7782352941176471, 2.208725, 0.9611066247880435, 2.3942907096774193, 0.5521064117647059]
Avg hOPT cluster: [3.122, 9.250588235294117, 7.5371304347826085, 4.159564102564102, 5.469478260869566]
Predictions PCE: [(2.466666666666667, 2.9), (0.8433333333333334, 0.2), (1.9866666666666666, 1.96), (2.546666666666667, 2.9), (1.4166666666666667, 0.61), (0.7966666666666667, 0.61), (1.9217333333333333, 1.96), (0.07253333333333332, 0.0052), (1.96, 1.7), (5.4433333333333325, 4.29), (0.86, 0.2), (3.7266666666666666, 1.7), (2.63, 3.05), (2.9633333333333334, 2.94), (3.296666666666667, 3.1), (0.47333333333333333, 0.44), (0.47333333333333333, 0.44), (1.78, 1.7), (2.63, 3.05), (2.796666666666667, 2.39), (2.0033333333333334, 2.39), (1.0923333333333334, 0.77), (2.0366666666666666, 2.6), (0.11266666666666668, 0.117), (0.42333333333333334, 0.38), (2.42, 2.39), (1.7199666666666669, 2.3), (2.4, 1.96), (2.1672666666666665, 2.7), (1.7199666666666669, 2.3), (2.4, 1.96), (2.58, 1.94), (0.0011200000000000001, 0.00086), (0.015533333333333335, 0.0019), (2.2699999999999996, 1.94), (0.09355633333333334, 0.000471), (0.07253333333333332, 0.0052), (0.10832000000000001, 0.0441), (0.7966666666666667, 0.61), (0.09362, 0.08), (0.07253333333333332, 0.0052), (0.7966666666666667, 0.61), (1.21, 0.62), (0.8099666666666666, 0.08), (1.3350666666666668, 1.2), (1.23, 0.62), (0.8692000000000001, 0.0052), (1.8933333333333335, 2.6), (1.6499999999999997, 1.44), (1.5099999999999998, 1.13), (1.39, 1.7), (4.5566666666666675, 2.16), (2.466666666666667, 2.9), (1.1633333333333333, 0.62), (1.7666666666666666, 1.7), (1.623333333333333, 1.8), (0.779, 0.08), (1.3666666666666665, 1.7), (1.0566666666666666, 0.77), (2.23, 1.7), (4.140000000000001, 4.36)]
Predictions hOPT: [(4.0, 3.9), (2.56, 2.58), (1.1333333333333333, 1.4), (1.1333333333333333, 1.4), (1.1333333333333333, 1.4), (1.1333333333333333, 1.4), (11.866666666666667, 12.5), (4.566666666666666, 6.4), (4.366666666666667, 3.2), (34.669999999999995, 48.0), (4.566666666666666, 6.4), (5.433333333333333, 6.8), (7.099999999999999, 6.8), (4.653333333333333, 4.56), (1.1333333333333333, 1.4), (1.1333333333333333, 1.4), (2.3066666666666666, 1.75), (2.3066666666666666, 1.75), (1.1333333333333333, 1.4), (1.1333333333333333, 1.4), (3.233333333333333, 1.5), (3.7999999999999994, 3.3), (1.7266666666666666, 2.1), (1.53, 0.28), (1.553333333333333, 0.34), (3.86, 2.3), (1.4000000000000001, 1.2), (3.393333333333333, 2.1), (13.633333333333335, 2.7), (19.066666666666666, 19.0), (25.166666666666668, 19.0), (13.633333333333335, 2.7), (17.400000000000002, 3.2), (1.7166666666666668, 1.85), (3.2266666666666666, 1.6), (11.523333333333333, 4.56), (0.5976666666666667, 0.058), (5.8, 4.8), (2.8200000000000003, 3.51), (3.98, 3.2), (2.1833333333333336, 1.6), (3.5533333333333332, 3.2), (3.5533333333333332, 3.2), (3.61, 3.51)]


mean_k_preds_pce = [p[0] for p in predictions_pce]
median_k_preds_pce = [p[1] for p in predictions_pce]

mean_k_preds_hopt = [p[0] for p in predictions_hopt]
median_k_preds_hopt = [p[1] for p in predictions_hopt]


print(f'PCE')
missing = get_missing(df, field='PCE (%)')
for name, _, _ in models:
    print(f'Model: {name}')
    preds_pce     = models_02_pce[name].predict(missing)
    out_preds_pce = models_out_02_pce[name].predict(missing)

    print(f'Mean')
    diff_mean_preds = np.abs(preds_pce-mean_k_preds_pce)
    diff_mean_out_preds = np.abs(out_preds_pce-mean_k_preds_pce)

    ax = sns.violinplot(data=[diff_mean_preds, diff_mean_out_preds])
    ax.set_xticklabels(['Baseline', 'No Outliers'])
    fig = plt.gcf()
    fig.savefig(f'figures/cluster_pce_{name}_mean.pdf', bbox_inches='tight')
    plt.show()
    #print(f'RMSE {rmse(preds_pce, mean_k_preds_pce)} {rmse(out_preds_pce, mean_k_preds_pce)}')

    print(f'Median')
    diff_median_preds = np.abs(preds_pce-median_k_preds_pce)
    diff_median_out_preds = np.abs(out_preds_pce-median_k_preds_pce)

    ax = sns.violinplot(data=[diff_median_preds, diff_median_out_preds])
    ax.set_xticklabels(['Baseline', 'No Outliers'])
    fig = plt.gcf()
    fig.savefig(f'figures/cluster_pce_{name}_median.pdf', bbox_inches='tight')
    plt.show()
    #print(f'RMSE {rmse(preds_pce, median_k_preds_pce)} {rmse(out_preds_pce, median_k_preds_pce)}')

    score_mae_mean = mean_absolute_error(preds_pce, mean_k_preds_pce)
    score_mse_mean = mean_squared_error(preds_pce, mean_k_preds_pce)
    score_r2_mean  = r2_score(preds_pce, mean_k_preds_pce)
                
    score_mae_median = mean_absolute_error(preds_pce, median_k_preds_pce)
    score_mse_median = mean_squared_error(preds_pce, median_k_preds_pce)
    score_r2_median  = r2_score(preds_pce, median_k_preds_pce)

    # print the results
    print(f'Baseline')
    print(f'| {"Aggregation":^17} | {"MAE":^6} | {"MSE":^6} | {"R2":^6} |')
    print(f'| ----------------- | ------ | ------ | ------ |')
    print(f'| {"Mean":<17} | {round(score_mae_mean, 2):>6} | {round(score_mse_mean, 2):>6} | {round(score_r2_mean, 2):>6} |')
    print(f'| {"Median":<17} | {round(score_mae_median, 2):>6} | {round(score_mse_median, 2):>6} | {round(score_r2_median, 2):>6} |')
    print()

    score_mae_mean_out = mean_absolute_error(out_preds_pce, mean_k_preds_pce)
    score_mse_mean_out = mean_squared_error(out_preds_pce, mean_k_preds_pce)
    score_r2_mean_out  = r2_score(mean_k_preds_pce, out_preds_pce)
                
    score_mae_median_out = mean_absolute_error(out_preds_pce, median_k_preds_pce)
    score_mse_median_out = mean_squared_error(out_preds_pce, median_k_preds_pce)
    score_r2_median_out  = r2_score(median_k_preds_pce, out_preds_pce)

    # print the results
    print(f'No Outliers')
    print(f'| {"Aggregation":^17} | {"MAE":^6} | {"MSE":^6} | {"R2":^6} |')
    print(f'| ----------------- | ------ | ------ | ------ |')
    print(f'| {"Mean":<17} | {round(score_mae_mean_out, 2):>6} | {round(score_mse_mean_out, 2):>6} | {round(score_r2_mean_out, 2):>6} |')
    print(f'| {"Median":<17} | {round(score_mae_median_out, 2):>6} | {round(score_mse_median_out, 2):>6} | {round(score_r2_median_out, 2):>6} |')
    print()

PCE
Model: Linear Regression
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   0.97 |   1.47 |  -1.87 |
| Median            |   1.02 |   1.48 |  -1.89 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   0.84 |   1.29 |   0.03 |
| Median            |   0.89 |   1.19 |   0.09 |

Model: K Neighbors
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |    0.8 |   1.35 |   -0.2 |
| Median            |   0.84 |   1.36 |  -0.21 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   0.68 |   0.99 |   0.26 |
| Median            |   0.74 |   0.81 |   0.38 |

Model: Random Forest
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   0.86 |   1.13 |  -1.23 |
| Median            |   0.91 |   1.24 |  -1.45 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   0.79 |   1.24 |   0.07 |
| Median            |   0.87 |    1.1 |   0.16 |

Model: Gradient Boosting
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   1.18 |   2.86 |  -0.13 |
| Median            |   1.21 |   2.78 |   -0.1 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   0.99 |    1.8 |  -0.35 |
| Median            |   1.03 |   1.58 |   -0.2 |

Model: XGBoost
Mean

Median


print(f'hOPT')
missing = get_missing(df, field='hopt (%)')
for name, _, _ in models:
    print(f'Model: {name}')
    preds_hopt     = models_02_hopt[name].predict(missing)
    out_preds_hopt = models_out_02_hopt[name].predict(missing)
    
    print(f'Mean')
    diff_mean_preds = np.abs(preds_hopt-mean_k_preds_hopt)
    diff_mean_out_preds = np.abs(out_preds_hopt-mean_k_preds_hopt)

    ax = sns.violinplot(data=[diff_mean_preds, diff_mean_out_preds])
    ax.set_xticklabels(['Baseline', 'No Outliers'])
    fig = plt.gcf()
    fig.savefig(f'figures/cluster_hopt_{name}_mean.pdf', bbox_inches='tight')
    plt.show()
    #print(f'RMSE {rmse(preds_pce, mean_k_preds_pce)} {rmse(out_preds_pce, mean_k_preds_pce)}')

    print(f'Median')
    diff_median_preds = np.abs(preds_hopt-median_k_preds_hopt)
    diff_median_out_preds = np.abs(out_preds_hopt-median_k_preds_hopt)

    ax = sns.violinplot(data=[diff_median_preds, diff_median_out_preds])
    ax.set_xticklabels(['Baseline', 'No Outliers'])
    fig = plt.gcf()
    fig.savefig(f'figures/cluster_hopt_{name}_median.pdf', bbox_inches='tight')
    plt.show()
    #print(f'RMSE {rmse(preds_pce, median_k_preds_pce)} {rmse(out_preds_pce, median_k_preds_pce)}')

    score_mae_mean = mean_absolute_error(preds_hopt, mean_k_preds_hopt)
    score_mse_mean = mean_squared_error(preds_hopt, mean_k_preds_hopt)
    score_r2_mean  = r2_score(preds_hopt, mean_k_preds_hopt)
                
    score_mae_median = mean_absolute_error(preds_hopt, median_k_preds_hopt)
    score_mse_median = mean_squared_error(preds_hopt, median_k_preds_hopt)
    score_r2_median  = r2_score(preds_hopt, median_k_preds_hopt)

    # print the results
    print(f'Baseline')
    print(f'| {"Aggregation":^17} | {"MAE":^6} | {"MSE":^6} | {"R2":^6} |')
    print(f'| ----------------- | ------ | ------ | ------ |')
    print(f'| {"Mean":<17} | {round(score_mae_mean, 2):>6} | {round(score_mse_mean, 2):>6} | {round(score_r2_mean, 2):>6} |')
    print(f'| {"Median":<17} | {round(score_mae_median, 2):>6} | {round(score_mse_median, 2):>6} | {round(score_r2_median, 2):>6} |')
    print()

    score_mae_mean_out = mean_absolute_error(out_preds_hopt, mean_k_preds_hopt)
    score_mse_mean_out = mean_squared_error(out_preds_hopt, mean_k_preds_hopt)
    score_r2_mean_out  = r2_score(mean_k_preds_hopt, out_preds_hopt)
                
    score_mae_median_out = mean_absolute_error(out_preds_hopt, median_k_preds_hopt)
    score_mse_median_out = mean_squared_error(out_preds_hopt, median_k_preds_hopt)
    score_r2_median_out  = r2_score(median_k_preds_hopt, out_preds_hopt)

    # print the results
    print(f'No Outliers')
    print(f'| {"Aggregation":^17} | {"MAE":^6} | {"MSE":^6} | {"R2":^6} |')
    print(f'| ----------------- | ------ | ------ | ------ |')
    print(f'| {"Mean":<17} | {round(score_mae_mean_out, 2):>6} | {round(score_mse_mean_out, 2):>6} | {round(score_r2_mean_out, 2):>6} |')
    print(f'| {"Median":<17} | {round(score_mae_median_out, 2):>6} | {round(score_mse_median_out, 2):>6} | {round(score_r2_median_out, 2):>6} |')
    print()

hOPT
Model: Linear Regression
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   4.99 |  47.15 |  -2.12 |
| Median            |   4.79 |  57.43 |   -2.8 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   3.84 |  56.54 |  -0.18 |
| Median            |   3.07 |  63.06 |  -0.06 |

Model: K Neighbors
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   2.65 |  23.39 |   0.49 |
| Median            |   1.98 |  15.15 |   0.67 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   3.67 |   57.3 |  -0.19 |
| Median            |   2.77 |  62.26 |  -0.04 |

Model: Random Forest
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   3.52 |  39.02 |   0.46 |
| Median            |   2.41 |  21.55 |    0.7 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   3.59 |  58.64 |  -0.22 |
| Median            |   2.87 |  64.29 |  -0.08 |

Model: Gradient Boosting
Mean

Median

Baseline
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   3.42 |  36.85 |   0.43 |
| Median            |   2.09 |  18.12 |   0.72 |

No Outliers
|    Aggregation    |  MAE   |  MSE   |   R2   |
| ----------------- | ------ | ------ | ------ |
| Mean              |   3.92 |  61.96 |  -0.29 |
| Median            |    3.2 |  67.39 |  -0.13 |

Model: XGBoost
Mean

Median


df_per_cluster = get_clusters_df(df, df_clustering_index, labels)

for i, df in enumerate(df_per_cluster):
    print(f'Cluster {i}')
    print(f'{df}')

Cluster 0
shape: (25, 12)
┌─────┬──────┬───────────┬──────────┬───┬────────┬────────┬──────────┬─────────┐
│ #   ┆ mat0 ┆ mat1      ┆ abs_peak ┆ … ┆ em_max ┆ QY (%) ┆ hopt (%) ┆ PCE (%) │
│ --- ┆ ---  ┆ ---       ┆ ---      ┆   ┆ ---    ┆ ---    ┆ ---      ┆ ---     │
│ i64 ┆ str  ┆ str       ┆ i64      ┆   ┆ i64    ┆ f64    ┆ f64      ┆ f64     │
╞═════╪══════╪═══════════╪══════════╪═══╪════════╪════════╪══════════╪═════════╡
│ 8   ┆ QD   ┆ solution  ┆ 800      ┆ … ┆ 1000   ┆ 30.0   ┆ 1.4      ┆ 3.2     │
│ 14  ┆ dye  ┆ solution  ┆ 466      ┆ … ┆ 900    ┆ 11.0   ┆ 0.6      ┆ null    │
│ 15  ┆ dye  ┆ solution  ┆ 557      ┆ … ┆ 900    ┆ 9.0    ┆ 0.5      ┆ null    │
│ 26  ┆ dye  ┆ film      ┆ 745      ┆ … ┆ 900    ┆ 25.0   ┆ null     ┆ 0.61    │
│ 27  ┆ dye  ┆ film      ┆ 745      ┆ … ┆ 900    ┆ 25.0   ┆ null     ┆ 1.24    │
│ 28  ┆ dye  ┆ film      ┆ 745      ┆ … ┆ 900    ┆ 25.0   ┆ null     ┆ 0.54    │
│ 29  ┆ dye  ┆ film      ┆ 745      ┆ … ┆ 900    ┆ 25.0   ┆ null     ┆ 1.41    │
│ 34  ┆ NP   ┆ bulk      ┆ 550      ┆ … ┆ 1000   ┆ 80.0   ┆ 6.8      ┆ null    │
│ 36  ┆ QD   ┆ film      ┆ 450      ┆ … ┆ 975    ┆ 40.0   ┆ null     ┆ null    │
│ 37  ┆ QD   ┆ waveguide ┆ 650      ┆ … ┆ 850    ┆ 63.0   ┆ 1.75     ┆ null    │
│ 38  ┆ QD   ┆ solution  ┆ 650      ┆ … ┆ 850    ┆ 63.0   ┆ 3.67     ┆ null    │
│ 55  ┆ QD   ┆ bulk      ┆ 500      ┆ … ┆ 1000   ┆ 50.0   ┆ null     ┆ 2.85    │
│ 57  ┆ QD   ┆ film      ┆ 450      ┆ … ┆ 1100   ┆ 91.0   ┆ 8.1      ┆ 2.94    │
│ 61  ┆ QD   ┆ bulk      ┆ 500      ┆ … ┆ 1000   ┆ 78.0   ┆ 6.4      ┆ 3.1     │
│ 62  ┆ QD   ┆ bulk      ┆ 640      ┆ … ┆ 1200   ┆ 40.0   ┆ null     ┆ 3.27    │
│ 63  ┆ QD   ┆ bulk      ┆ 415      ┆ … ┆ 1240   ┆ 60.3   ┆ null     ┆ 3.94    │
│ 72  ┆ dye  ┆ film      ┆ 760      ┆ … ┆ 900    ┆ 24.0   ┆ null     ┆ 0.44    │
│ 73  ┆ dye  ┆ film      ┆ 760      ┆ … ┆ 900    ┆ 24.0   ┆ null     ┆ 0.28    │
│ 74  ┆ dye  ┆ film      ┆ 700      ┆ … ┆ 900    ┆ 30.0   ┆ null     ┆ 0.62    │
│ 75  ┆ dye  ┆ film      ┆ 700      ┆ … ┆ 900    ┆ 30.0   ┆ null     ┆ 0.36    │
│ 76  ┆ dye  ┆ film      ┆ 738      ┆ … ┆ 900    ┆ 23.0   ┆ null     ┆ 0.41    │
│ 77  ┆ dye  ┆ film      ┆ 738      ┆ … ┆ 900    ┆ 23.0   ┆ null     ┆ 0.28    │
│ 79  ┆ QD   ┆ bulk      ┆ 763      ┆ … ┆ 1050   ┆ 70.0   ┆ null     ┆ 4.74    │
│ 106 ┆ dye  ┆ film      ┆ 770      ┆ … ┆ 950    ┆ 16.0   ┆ 1.5      ┆ null    │
│ 110 ┆ dye  ┆ fiber     ┆ 780      ┆ … ┆ 850    ┆ 21.0   ┆ 0.5      ┆ null    │
└─────┴──────┴───────────┴──────────┴───┴────────┴────────┴──────────┴─────────┘
Cluster 1
shape: (46, 12)
┌─────┬─────────┬──────────┬──────────┬───┬────────┬────────┬──────────┬─────────┐
│ #   ┆ mat0    ┆ mat1     ┆ abs_peak ┆ … ┆ em_max ┆ QY (%) ┆ hopt (%) ┆ PCE (%) │
│ --- ┆ ---     ┆ ---      ┆ ---      ┆   ┆ ---    ┆ ---    ┆ ---      ┆ ---     │
│ i64 ┆ str     ┆ str      ┆ i64      ┆   ┆ i64    ┆ f64    ┆ f64      ┆ f64     │
╞═════╪═════════╪══════════╪══════════╪═══╪════════╪════════╪══════════╪═════════╡
│ 1   ┆ dye     ┆ film     ┆ 578      ┆ … ┆ 750    ┆ 98.0   ┆ 18.8     ┆ null    │
│ 9   ┆ QD      ┆ solution ┆ 600      ┆ … ┆ 700    ┆ 50.0   ┆ 0.5      ┆ 1.2     │
│ 11  ┆ QD      ┆ solution ┆ 376      ┆ … ┆ 700    ┆ 50.0   ┆ 0.3      ┆ null    │
│ 12  ┆ dye     ┆ solution ┆ 413      ┆ … ┆ 800    ┆ 67.0   ┆ 3.4      ┆ null    │
│ 13  ┆ dye     ┆ solution ┆ 550      ┆ … ┆ 750    ┆ 95.0   ┆ 2.6      ┆ null    │
│ 16  ┆ polymer ┆ solution ┆ 460      ┆ … ┆ 800    ┆ 45.0   ┆ 1.0      ┆ null    │
│ 17  ┆ polymer ┆ solution ┆ 467      ┆ … ┆ 700    ┆ 48.0   ┆ 0.9      ┆ null    │
│ 25  ┆ dye     ┆ bulk     ┆ 580      ┆ … ┆ 800    ┆ 100.0  ┆ null     ┆ 0.0018  │
│ 30  ┆ dye     ┆ bulk     ┆ 525      ┆ … ┆ 800    ┆ 97.6   ┆ null     ┆ 2.6     │
│ 51  ┆ NP      ┆ film     ┆ 500      ┆ … ┆ 600    ┆ 92.0   ┆ null     ┆ null    │
│ 56  ┆ QD      ┆ bulk     ┆ 500      ┆ … ┆ 700    ┆ 35.9   ┆ 1.45     ┆ null    │
│ 68  ┆ dye     ┆ bulk     ┆ 478      ┆ … ┆ 800    ┆ 61.1   ┆ 22.0     ┆ null    │
│ 69  ┆ dye     ┆ bulk     ┆ 513      ┆ … ┆ 800    ┆ 24.8   ┆ 3.3      ┆ null    │
│ 71  ┆ dye     ┆ bulk     ┆ 473      ┆ … ┆ 800    ┆ 44.3   ┆ 24.7     ┆ null    │
│ 84  ┆ Ln      ┆ bulk     ┆ 590      ┆ … ┆ 700    ┆ 65.0   ┆ null     ┆ 11.3    │
│ 98  ┆ dye     ┆ film     ┆ 520      ┆ … ┆ 700    ┆ 78.0   ┆ 0.08     ┆ null    │
│ 99  ┆ dye     ┆ fiber    ┆ 520      ┆ … ┆ 700    ┆ 78.0   ┆ 1.6      ┆ 0.0052  │
│ 100 ┆ dye     ┆ fiber    ┆ 520      ┆ … ┆ 700    ┆ 93.0   ┆ 8.0      ┆ 0.0024  │
│ 105 ┆ dye     ┆ bulk     ┆ 570      ┆ … ┆ 750    ┆ 80.0   ┆ 14.5     ┆ 2.16    │
│ 107 ┆ dye     ┆ bulk     ┆ 665      ┆ … ┆ 750    ┆ 12.0   ┆ 3.7      ┆ 0.1     │
│ 109 ┆ dye     ┆ fiber    ┆ 560      ┆ … ┆ 700    ┆ 95.0   ┆ 2.1      ┆ null    │
│ 112 ┆ dye     ┆ fiber    ┆ 560      ┆ … ┆ 700    ┆ 95.0   ┆ null     ┆ 0.21    │
│ 113 ┆ QD      ┆ bulk     ┆ 580      ┆ … ┆ 700    ┆ 10.0   ┆ null     ┆ 2.1     │
│ 114 ┆ QD      ┆ bulk     ┆ 580      ┆ … ┆ 700    ┆ 60.0   ┆ null     ┆ 2.1     │
│ 115 ┆ dye     ┆ bulk     ┆ 575      ┆ … ┆ 720    ┆ 95.0   ┆ null     ┆ 3.3     │
│ 116 ┆ QD      ┆ bulk     ┆ 580      ┆ … ┆ 700    ┆ 10.0   ┆ null     ┆ 2.1     │
│ 117 ┆ QD      ┆ bulk     ┆ 450      ┆ … ┆ 680    ┆ 44.0   ┆ null     ┆ 2.8     │
│ 118 ┆ QD      ┆ bulk     ┆ 450      ┆ … ┆ 650    ┆ 86.0   ┆ 48.0     ┆ null    │
│ 121 ┆ Ln      ┆ bulk     ┆ 530      ┆ … ┆ 750    ┆ 83.0   ┆ null     ┆ 1.44    │
│ 122 ┆ QD      ┆ bulk     ┆ 473      ┆ … ┆ 700    ┆ 45.0   ┆ 1.0      ┆ null    │
│ 124 ┆ QD      ┆ bulk     ┆ 470      ┆ … ┆ 700    ┆ 20.0   ┆ 2.01     ┆ null    │
│ 125 ┆ dye     ┆ bulk     ┆ 521      ┆ … ┆ 700    ┆ 93.0   ┆ 54.0     ┆ null    │
│ 128 ┆ dye     ┆ film     ┆ 545      ┆ … ┆ 800    ┆ 50.0   ┆ 12.5     ┆ null    │
│ 129 ┆ dye     ┆ solution ┆ 498      ┆ … ┆ 700    ┆ 30.0   ┆ 6.88     ┆ 0.27    │
│ 130 ┆ dye     ┆ solution ┆ 569      ┆ … ┆ 750    ┆ 61.0   ┆ 2.58     ┆ null    │
│ 134 ┆ CD      ┆ bulk     ┆ 720      ┆ … ┆ 600    ┆ 65.0   ┆ null     ┆ 8.75    │
│ 136 ┆ CD      ┆ film     ┆ 557      ┆ … ┆ 700    ┆ 70.0   ┆ 2.3      ┆ null    │
│ 138 ┆ dye     ┆ bulk     ┆ 575      ┆ … ┆ 700    ┆ 96.0   ┆ 37.7     ┆ null    │
│ 142 ┆ dye     ┆ bulk     ┆ 575      ┆ … ┆ 720    ┆ 95.0   ┆ 19.0     ┆ 2.9     │
│ 143 ┆ QD      ┆ bulk     ┆ 480      ┆ … ┆ 700    ┆ 15.7   ┆ 3.2      ┆ 0.62    │
│ 146 ┆ QDdye   ┆ bulk     ┆ 500      ┆ … ┆ 750    ┆ 32.7   ┆ 1.0      ┆ null    │
│ 164 ┆ CD      ┆ film     ┆ 555      ┆ … ┆ 800    ┆ 17.6   ┆ 3.0      ┆ 2.7     │
│ 165 ┆ CD      ┆ film     ┆ 450      ┆ … ┆ 800    ┆ 60.0   ┆ 4.3      ┆ 3.8     │
│ 171 ┆ CD      ┆ film     ┆ 410      ┆ … ┆ 750    ┆ 7.6    ┆ 2.77     ┆ 1.96    │
│ 173 ┆ QD      ┆ bulk     ┆ 600      ┆ … ┆ 700    ┆ 30.0   ┆ 2.7      ┆ 0.38    │
│ 200 ┆ dye     ┆ solution ┆ 660      ┆ … ┆ 800    ┆ 31.0   ┆ 2.65     ┆ 0.21    │
└─────┴─────────┴──────────┴──────────┴───┴────────┴────────┴──────────┴─────────┘
Cluster 2
shape: (23, 12)
┌─────┬─────────┬──────────┬──────────┬───┬────────┬────────┬──────────┬──────────┐
│ #   ┆ mat0    ┆ mat1     ┆ abs_peak ┆ … ┆ em_max ┆ QY (%) ┆ hopt (%) ┆ PCE (%)  │
│ --- ┆ ---     ┆ ---      ┆ ---      ┆   ┆ ---    ┆ ---    ┆ ---      ┆ ---      │
│ i64 ┆ str     ┆ str      ┆ i64      ┆   ┆ i64    ┆ f64    ┆ f64      ┆ f64      │
╞═════╪═════════╪══════════╪══════════╪═══╪════════╪════════╪══════════╪══════════╡
│ 177 ┆ Ln      ┆ film     ┆ 450      ┆ … ┆ 570    ┆ 44.0   ┆ 4.8      ┆ 0.054    │
│ 178 ┆ Ln      ┆ film     ┆ 400      ┆ … ┆ 470    ┆ 37.0   ┆ 7.7      ┆ 0.058    │
│ 179 ┆ CD      ┆ film     ┆ 425      ┆ … ┆ 400    ┆ 11.0   ┆ 13.1     ┆ 0.053    │
│ 180 ┆ Ln      ┆ film     ┆ 450      ┆ … ┆ 570    ┆ 44.0   ┆ 5.2      ┆ 0.046    │
│ 181 ┆ Ln      ┆ film     ┆ 400      ┆ … ┆ 470    ┆ 37.0   ┆ 7.7      ┆ 0.047    │
│ 182 ┆ CD      ┆ film     ┆ 425      ┆ … ┆ 400    ┆ 11.0   ┆ 12.8     ┆ 0.041    │
│ 183 ┆ Ln      ┆ film     ┆ 450      ┆ … ┆ 570    ┆ 59.0   ┆ 6.7      ┆ 0.074    │
│ 184 ┆ Ln      ┆ film     ┆ 400      ┆ … ┆ 470    ┆ 54.0   ┆ 8.5      ┆ 0.065    │
│ 185 ┆ Ln      ┆ film     ┆ 450      ┆ … ┆ 570    ┆ 59.0   ┆ 10.7     ┆ 0.096    │
│ 186 ┆ Ln      ┆ film     ┆ 400      ┆ … ┆ 470    ┆ 54.0   ┆ 8.7      ┆ 0.053    │
│ 187 ┆ Ln      ┆ film     ┆ 450      ┆ … ┆ 570    ┆ 59.0   ┆ 11.7     ┆ 0.142    │
│ 188 ┆ Ln      ┆ film     ┆ 400      ┆ … ┆ 470    ┆ 54.0   ┆ 16.5     ┆ 0.136    │
│ 189 ┆ dye     ┆ film     ┆ 650      ┆ … ┆ 600    ┆ 4.0    ┆ 2.6      ┆ 0.044    │
│ 190 ┆ polymer ┆ film     ┆ 500      ┆ … ┆ 400    ┆ 47.0   ┆ 5.71     ┆ 2.29     │
│ 191 ┆ polymer ┆ film     ┆ 500      ┆ … ┆ 450    ┆ 57.0   ┆ 9.112    ┆ 2.32     │
│ 192 ┆ polymer ┆ film     ┆ 500      ┆ … ┆ 400    ┆ 68.0   ┆ 12.08    ┆ 2.47     │
│ 193 ┆ polymer ┆ film     ┆ 500      ┆ … ┆ 400    ┆ 47.0   ┆ 5.71     ┆ 4.38     │
│ 194 ┆ polymer ┆ film     ┆ 500      ┆ … ┆ 450    ┆ 57.0   ┆ 9.112    ┆ 4.62     │
│ 195 ┆ polymer ┆ film     ┆ 500      ┆ … ┆ 400    ┆ 68.0   ┆ 12.08    ┆ 4.92     │
│ 196 ┆ NP      ┆ bulk     ┆ 600      ┆ … ┆ 490    ┆ 65.0   ┆ 0.15     ┆ 0.049413 │
│ 197 ┆ dye     ┆ bulk     ┆ 600      ┆ … ┆ 575    ┆ 70.0   ┆ 0.16     ┆ 0.050786 │
│ 198 ┆ NPdye   ┆ bulk     ┆ 600      ┆ … ┆ 500    ┆ 68.0   ┆ 0.22     ┆ 0.07531  │
│ 199 ┆ QD      ┆ solution ┆ 510      ┆ … ┆ 475    ┆ 89.0   ┆ 2.32     ┆ 0.020944 │
└─────┴─────────┴──────────┴──────────┴───┴────────┴────────┴──────────┴──────────┘
Cluster 3
shape: (51, 12)
┌─────┬──────┬──────────┬──────────┬───┬────────┬────────┬──────────┬──────────┐
│ #   ┆ mat0 ┆ mat1     ┆ abs_peak ┆ … ┆ em_max ┆ QY (%) ┆ hopt (%) ┆ PCE (%)  │
│ --- ┆ ---  ┆ ---      ┆ ---      ┆   ┆ ---    ┆ ---    ┆ ---      ┆ ---      │
│ i64 ┆ str  ┆ str      ┆ i64      ┆   ┆ i64    ┆ f64    ┆ f64      ┆ f64      │
╞═════╪══════╪══════════╪══════════╪═══╪════════╪════════╪══════════╪══════════╡
│ 18  ┆ dye  ┆ film     ┆ 403      ┆ … ┆ 600    ┆ 40.8   ┆ 7.7      ┆ null     │
│ 19  ┆ dye  ┆ bulk     ┆ 374      ┆ … ┆ 600    ┆ 100.0  ┆ null     ┆ null     │
│ 23  ┆ dye  ┆ bulk     ┆ 340      ┆ … ┆ 700    ┆ 14.0   ┆ 0.25     ┆ null     │
│ 24  ┆ dye  ┆ bulk     ┆ 340      ┆ … ┆ 600    ┆ 78.0   ┆ 0.4      ┆ null     │
│ 43  ┆ CD   ┆ film     ┆ 350      ┆ … ┆ 650    ┆ 45.0   ┆ 12.0     ┆ null     │
│ 44  ┆ CD   ┆ film     ┆ 358      ┆ … ┆ 600    ┆ 94.0   ┆ 3.9      ┆ null     │
│ 46  ┆ CD   ┆ bulk     ┆ 340      ┆ … ┆ 700    ┆ 40.0   ┆ 0.92     ┆ null     │
│ 47  ┆ CDQD ┆ tandem   ┆ 450      ┆ … ┆ 700    ┆ 45.0   ┆ 1.4      ┆ null     │
│ 49  ┆ CDQD ┆ bulk     ┆ 400      ┆ … ┆ 550    ┆ 70.0   ┆ null     ┆ 3.05     │
│ 52  ┆ NP   ┆ bulk     ┆ 325      ┆ … ┆ 525    ┆ 58.0   ┆ 2.4      ┆ 1.8      │
│ 54  ┆ CD   ┆ bulk     ┆ 440      ┆ … ┆ 700    ┆ 25.0   ┆ 1.2      ┆ null     │
│ 58  ┆ QD   ┆ bulk     ┆ 350      ┆ … ┆ 775    ┆ 81.0   ┆ 26.5     ┆ 8.71     │
│ 65  ┆ QD   ┆ bulk     ┆ 360      ┆ … ┆ 700    ┆ 53.0   ┆ null     ┆ null     │
│ 82  ┆ dye  ┆ bulk     ┆ 450      ┆ … ┆ 600    ┆ 17.0   ┆ null     ┆ 8.99     │
│ 88  ┆ Ln   ┆ film     ┆ 290      ┆ … ┆ 650    ┆ 40.0   ┆ 8.8      ┆ null     │
│ 91  ┆ Ln   ┆ film     ┆ 325      ┆ … ┆ 650    ┆ 12.0   ┆ 1.7      ┆ null     │
│ 123 ┆ QD   ┆ bulk     ┆ 350      ┆ … ┆ 750    ┆ 56.0   ┆ null     ┆ 8.71     │
│ 126 ┆ CD   ┆ film     ┆ 450      ┆ … ┆ 700    ┆ 11.0   ┆ 7.58     ┆ 6.0      │
│ 131 ┆ dye  ┆ solution ┆ 488      ┆ … ┆ 600    ┆ 51.0   ┆ 3.3      ┆ 0.35     │
│ 132 ┆ CD   ┆ bulk     ┆ 460      ┆ … ┆ 500    ┆ 54.0   ┆ 2.7      ┆ null     │
│ 133 ┆ CD   ┆ bulk     ┆ 340      ┆ … ┆ 700    ┆ 6.0    ┆ 5.84     ┆ null     │
│ 135 ┆ CD   ┆ film     ┆ 420      ┆ … ┆ 700    ┆ 40.0   ┆ 1.6      ┆ 0.7      │
│ 137 ┆ CD   ┆ film     ┆ 420      ┆ … ┆ 600    ┆ 67.0   ┆ 2.2      ┆ 1.13     │
│ 139 ┆ CD   ┆ solution ┆ 491      ┆ … ┆ 700    ┆ 82.0   ┆ 5.43     ┆ 0.18     │
│ 140 ┆ CD   ┆ film     ┆ 510      ┆ … ┆ 650    ┆ 78.0   ┆ 0.058    ┆ 0.00083  │
│ 141 ┆ CD   ┆ film     ┆ 510      ┆ … ┆ 650    ┆ 78.0   ┆ 1.7      ┆ 0.014    │
│ 144 ┆ CD   ┆ film     ┆ 405      ┆ … ┆ 700    ┆ 70.0   ┆ 3.2      ┆ 1.9      │
│ 145 ┆ CD   ┆ film     ┆ 405      ┆ … ┆ 700    ┆ 65.0   ┆ 2.9      ┆ 1.7      │
│ 147 ┆ CD   ┆ film     ┆ 347      ┆ … ┆ 700    ┆ 61.0   ┆ 4.56     ┆ 4.1      │
│ 148 ┆ Ln   ┆ bulk     ┆ 405      ┆ … ┆ 700    ┆ 81.0   ┆ 3.4      ┆ 1.37     │
│ 149 ┆ CD   ┆ film     ┆ 490      ┆ … ┆ 650    ┆ 80.5   ┆ null     ┆ 2.06     │
│ 150 ┆ CD   ┆ film     ┆ 490      ┆ … ┆ 650    ┆ 80.5   ┆ 4.8      ┆ 4.36     │
│ 151 ┆ CD   ┆ film     ┆ 380      ┆ … ┆ 700    ┆ 11.54  ┆ 1.36     ┆ null     │
│ 152 ┆ QD   ┆ film     ┆ 300      ┆ … ┆ 550    ┆ 35.91  ┆ 3.08     ┆ null     │
│ 154 ┆ CDQD ┆ film     ┆ 320      ┆ … ┆ 700    ┆ 23.0   ┆ 1.89     ┆ null     │
│ 155 ┆ CDQD ┆ film     ┆ 320      ┆ … ┆ 700    ┆ 22.0   ┆ 2.54     ┆ null     │
│ 156 ┆ CDQD ┆ film     ┆ 320      ┆ … ┆ 700    ┆ 26.0   ┆ 3.76     ┆ null     │
│ 157 ┆ CD   ┆ film     ┆ 350      ┆ … ┆ 750    ┆ 35.0   ┆ null     ┆ 1.9      │
│ 158 ┆ CD   ┆ film     ┆ 380      ┆ … ┆ 700    ┆ 35.0   ┆ null     ┆ 1.7      │
│ 159 ┆ CD   ┆ film     ┆ 370      ┆ … ┆ 775    ┆ 35.0   ┆ null     ┆ 2.3      │
│ 160 ┆ CD   ┆ film     ┆ 400      ┆ … ┆ 700    ┆ 33.0   ┆ 4.5      ┆ 0.117    │
│ 161 ┆ CD   ┆ bulk     ┆ 400      ┆ … ┆ 700    ┆ 41.0   ┆ 5.89     ┆ 0.16     │
│ 162 ┆ CD   ┆ bulk     ┆ 400      ┆ … ┆ 700    ┆ 41.0   ┆ 3.13     ┆ 0.061    │
│ 168 ┆ CD   ┆ bulk     ┆ 470      ┆ … ┆ 650    ┆ 9.6    ┆ 9.3      ┆ null     │
│ 169 ┆ CD   ┆ film     ┆ 380      ┆ … ┆ 700    ┆ 41.52  ┆ 3.51     ┆ 2.39     │
│ 170 ┆ CD   ┆ film     ┆ 355      ┆ … ┆ 650    ┆ 15.01  ┆ 2.76     ┆ 1.94     │
│ 172 ┆ CD   ┆ film     ┆ 400      ┆ … ┆ 750    ┆ 22.0   ┆ 4.03     ┆ 2.92     │
│ 174 ┆ QD   ┆ bulk     ┆ 350      ┆ … ┆ 700    ┆ 91.0   ┆ null     ┆ 4.29     │
│ 175 ┆ QD   ┆ bulk     ┆ 350      ┆ … ┆ 700    ┆ 91.0   ┆ null     ┆ 0.55     │
│ 176 ┆ QD   ┆ bulk     ┆ 350      ┆ … ┆ 700    ┆ 11.0   ┆ null     ┆ 0.77     │
│ 202 ┆ CD   ┆ film     ┆ 510      ┆ … ┆ 650    ┆ 78.0   ┆ 0.035    ┆ 0.000182 │
└─────┴──────┴──────────┴──────────┴───┴────────┴────────┴──────────┴──────────┘
Cluster 4
shape: (28, 12)
┌─────┬──────┬───────┬──────────┬───┬────────┬────────┬──────────┬──────────┐
│ #   ┆ mat0 ┆ mat1  ┆ abs_peak ┆ … ┆ em_max ┆ QY (%) ┆ hopt (%) ┆ PCE (%)  │
│ --- ┆ ---  ┆ ---   ┆ ---      ┆   ┆ ---    ┆ ---    ┆ ---      ┆ ---      │
│ i64 ┆ str  ┆ str   ┆ i64      ┆   ┆ i64    ┆ f64    ┆ f64      ┆ f64      │
╞═════╪══════╪═══════╪══════════╪═══╪════════╪════════╪══════════╪══════════╡
│ 20  ┆ dye  ┆ bulk  ┆ 370      ┆ … ┆ 750    ┆ 67.0   ┆ 5.5      ┆ null     │
│ 31  ┆ NP   ┆ bulk  ┆ 375      ┆ … ┆ 900    ┆ 45.0   ┆ 4.25     ┆ 1.33     │
│ 39  ┆ QD   ┆ film  ┆ 480      ┆ … ┆ 670    ┆ 36.2   ┆ 2.95     ┆ 2.25     │
│ 50  ┆ NP   ┆ film  ┆ 400      ┆ … ┆ 700    ┆ 25.0   ┆ 1.85     ┆ null     │
│ 67  ┆ dye  ┆ bulk  ┆ 446      ┆ … ┆ 800    ┆ 89.5   ┆ 31.3     ┆ null     │
│ 70  ┆ dye  ┆ bulk  ┆ 449      ┆ … ┆ 800    ┆ 80.0   ┆ 27.8     ┆ null     │
│ 80  ┆ dye  ┆ bulk  ┆ 491      ┆ … ┆ 650    ┆ 95.0   ┆ 23.7     ┆ 2.81     │
│ 85  ┆ Ln   ┆ film  ┆ 380      ┆ … ┆ 710    ┆ 30.5   ┆ 0.34     ┆ 0.0019   │
│ 86  ┆ Ln   ┆ film  ┆ 360      ┆ … ┆ 700    ┆ 1.6    ┆ 0.27     ┆ 0.00078  │
│ 87  ┆ Ln   ┆ film  ┆ 370      ┆ … ┆ 710    ┆ 27.0   ┆ 3.2      ┆ 0.007    │
│ 89  ┆ Ln   ┆ film  ┆ 350      ┆ … ┆ 710    ┆ 34.0   ┆ 4.3      ┆ null     │
│ 90  ┆ Ln   ┆ film  ┆ 325      ┆ … ┆ 710    ┆ 8.0    ┆ 1.2      ┆ null     │
│ 93  ┆ Ln   ┆ film  ┆ 370      ┆ … ┆ 710    ┆ 63.0   ┆ 9.0      ┆ null     │
│ 94  ┆ Ln   ┆ film  ┆ 370      ┆ … ┆ 710    ┆ 61.0   ┆ 1.2      ┆ 0.2      │
│ 95  ┆ Ln   ┆ film  ┆ 380      ┆ … ┆ 710    ┆ 23.0   ┆ 0.43     ┆ 0.03     │
│ 96  ┆ Ln   ┆ film  ┆ 360      ┆ … ┆ 710    ┆ 30.0   ┆ 0.01     ┆ 0.0006   │
│ 97  ┆ Ln   ┆ fiber ┆ 360      ┆ … ┆ 710    ┆ 85.0   ┆ 2.3      ┆ 0.00086  │
│ 101 ┆ Ln   ┆ film  ┆ 340      ┆ … ┆ 710    ┆ 44.0   ┆ null     ┆ 0.0441   │
│ 102 ┆ Ln   ┆ film  ┆ 405      ┆ … ┆ 710    ┆ 44.0   ┆ null     ┆ 0.0499   │
│ 103 ┆ Ln   ┆ film  ┆ 350      ┆ … ┆ 710    ┆ 73.0   ┆ 0.28     ┆ 0.28     │
│ 104 ┆ Ln   ┆ film  ┆ 320      ┆ … ┆ 710    ┆ 86.0   ┆ null     ┆ null     │
│ 108 ┆ Ln   ┆ fiber ┆ 370      ┆ … ┆ 710    ┆ 89.0   ┆ 0.7      ┆ null     │
│ 111 ┆ Ln   ┆ fiber ┆ 370      ┆ … ┆ 710    ┆ 89.0   ┆ null     ┆ 0.08     │
│ 120 ┆ QD   ┆ film  ┆ 396      ┆ … ┆ 700    ┆ 53.0   ┆ null     ┆ null     │
│ 153 ┆ QD   ┆ film  ┆ 320      ┆ … ┆ 700    ┆ 32.97  ┆ 2.55     ┆ null     │
│ 163 ┆ CD   ┆ film  ┆ 404      ┆ … ┆ 750    ┆ 86.4   ┆ 2.6      ┆ 2.3      │
│ 201 ┆ Ln   ┆ film  ┆ 370      ┆ … ┆ 720    ┆ 60.0   ┆ 0.02     ┆ 0.000198 │
│ 203 ┆ Ln   ┆ film  ┆ 370      ┆ … ┆ 720    ┆ 60.0   ┆ 0.048    ┆ 0.000471 │
└─────┴──────┴───────┴──────────┴───┴────────┴────────┴──────────┴──────────┘


plot_stats_per_cluster(df, df_clustering_index, labels)

Cluster: 0

Cluster: 1

Cluster: 2

Cluster: 3

Cluster: 4


X = df[['abs_peak', 'abs_min', 'abs_max', 'em_peak', 'em_min', 'em_max', 'QY (%)', 'hopt (%)', 'PCE (%)']].to_numpy()
X[np.isnan(X)] = 0
X

array([[3.700e+02, 3.000e+02, 4.500e+02, 6.500e+02, 4.500e+02, 7.500e+02,
        6.700e+01, 5.500e+00, 0.000e+00],
       [3.750e+02, 3.000e+02, 4.500e+02, 7.500e+02, 4.000e+02, 9.000e+02,
        4.500e+01, 4.250e+00, 1.330e+00],
       [4.800e+02, 3.000e+02, 5.000e+02, 6.190e+02, 5.700e+02, 6.700e+02,
        3.620e+01, 2.950e+00, 2.250e+00],
       [4.000e+02, 3.000e+02, 5.000e+02, 6.000e+02, 5.000e+02, 7.000e+02,
        2.500e+01, 1.850e+00, 0.000e+00],
       [4.460e+02, 2.500e+02, 5.000e+02, 5.530e+02, 5.000e+02, 8.000e+02,
        8.950e+01, 3.130e+01, 0.000e+00],
       [4.490e+02, 2.500e+02, 5.500e+02, 5.710e+02, 5.000e+02, 8.000e+02,
        8.000e+01, 2.780e+01, 0.000e+00],
       [4.910e+02, 3.000e+02, 5.000e+02, 5.810e+02, 5.500e+02, 6.500e+02,
        9.500e+01, 2.370e+01, 2.810e+00],
       [3.800e+02, 2.500e+02, 4.000e+02, 6.120e+02, 5.700e+02, 7.100e+02,
        3.050e+01, 3.400e-01, 1.900e-03],
       [3.600e+02, 2.500e+02, 3.800e+02, 5.450e+02, 4.500e+02, 7.000e+02,
        1.600e+00, 2.700e-01, 7.800e-04],
       [3.700e+02, 2.900e+02, 3.800e+02, 6.110e+02, 5.700e+02, 7.100e+02,
        2.700e+01, 3.200e+00, 7.000e-03],
       [3.500e+02, 2.400e+02, 4.200e+02, 6.120e+02, 5.700e+02, 7.100e+02,
        3.400e+01, 4.300e+00, 0.000e+00],
       [3.250e+02, 2.400e+02, 4.000e+02, 6.120e+02, 5.700e+02, 7.100e+02,
        8.000e+00, 1.200e+00, 0.000e+00],
       [3.700e+02, 2.400e+02, 4.000e+02, 6.120e+02, 5.700e+02, 7.100e+02,
        6.300e+01, 9.000e+00, 0.000e+00],
       [3.700e+02, 3.000e+02, 3.800e+02, 6.150e+02, 5.700e+02, 7.100e+02,
        6.100e+01, 1.200e+00, 2.000e-01],
       [3.800e+02, 2.400e+02, 3.800e+02, 6.120e+02, 5.700e+02, 7.100e+02,
        2.300e+01, 4.300e-01, 3.000e-02],
       [3.600e+02, 2.400e+02, 3.800e+02, 6.120e+02, 5.700e+02, 7.100e+02,
        3.000e+01, 1.000e-02, 6.000e-04],
       [3.600e+02, 2.400e+02, 4.200e+02, 6.150e+02, 5.700e+02, 7.100e+02,
        8.500e+01, 2.300e+00, 8.600e-04],
       [3.400e+02, 2.500e+02, 3.800e+02, 6.130e+02, 5.700e+02, 7.100e+02,
        4.400e+01, 0.000e+00, 4.410e-02],
       [4.050e+02, 2.500e+02, 4.200e+02, 6.130e+02, 5.700e+02, 7.100e+02,
        4.400e+01, 0.000e+00, 4.990e-02],
       [3.500e+02, 2.500e+02, 4.000e+02, 6.130e+02, 5.700e+02, 7.100e+02,
        7.300e+01, 2.800e-01, 2.800e-01],
       [3.200e+02, 2.500e+02, 3.500e+02, 6.130e+02, 5.700e+02, 7.100e+02,
        8.600e+01, 0.000e+00, 0.000e+00],
       [3.700e+02, 3.000e+02, 4.500e+02, 6.150e+02, 5.700e+02, 7.100e+02,
        8.900e+01, 7.000e-01, 0.000e+00],
       [3.700e+02, 3.000e+02, 4.500e+02, 6.150e+02, 5.700e+02, 7.100e+02,
        8.900e+01, 0.000e+00, 8.000e-02],
       [3.960e+02, 3.500e+02, 4.500e+02, 5.820e+02, 5.000e+02, 7.000e+02,
        5.300e+01, 0.000e+00, 0.000e+00],
       [3.200e+02, 3.000e+02, 5.500e+02, 6.700e+02, 6.000e+02, 7.000e+02,
        3.297e+01, 2.550e+00, 0.000e+00],
       [4.040e+02, 3.000e+02, 5.500e+02, 5.940e+02, 5.000e+02, 7.500e+02,
        8.640e+01, 2.600e+00, 2.300e+00],
       [3.700e+02, 2.500e+02, 4.000e+02, 6.120e+02, 5.700e+02, 7.200e+02,
        6.000e+01, 2.000e-02, 1.980e-04],
       [3.700e+02, 2.500e+02, 4.000e+02, 6.120e+02, 5.700e+02, 7.200e+02,
        6.000e+01, 4.800e-02, 4.710e-04]])


# Get the Original Values
QY = X.T[6]
hopt = X.T[7]
PCE = X.T[8]

# Get the Masks for the non-zero values
QY_MASK = QY != 0
hopt_MASK = hopt != 0
PCE_MASK = PCE != 0

# Convert boolean mask to index one
QY_MASK = [i for i in range(len(QY_MASK)) if QY_MASK[i]]
hopt_MASK = [i for i in range(len(hopt_MASK)) if hopt_MASK[i]]
PCE_MASK = [i for i in range(len(PCE_MASK)) if PCE_MASK[i]]

# Compute the average and standard deviation
QY_AVG = np.average(QY[QY_MASK])
QY_STD = np.std(QY[QY_MASK])

hopt_AVG = np.average(hopt[hopt_MASK])
hopt_STD = np.std(hopt[hopt_MASK])

PCE_AVG = np.average(PCE[PCE_MASK])
PCE_STD = np.std(PCE[PCE_MASK])

test = .3
random.seed(42)

# Select the index of the test set
QY_TEST_SET_INDEX = random.sample(QY_MASK, int(len(QY_MASK)*test))
hopt_TEST_SET_INDEX = random.sample(hopt_MASK, int(len(hopt_MASK)*test))
PCE_TEST_SET_INDEX = random.sample(PCE_MASK, int(len(PCE_MASK)*test))

print(f'{QY_TEST_SET_INDEX}\n{hopt_TEST_SET_INDEX}\n{PCE_TEST_SET_INDEX}')

[20, 3, 0, 23, 8, 7, 22, 4]
[3, 26, 19, 2, 21, 13]
[2, 1, 27, 7, 22]


# Store original values from the test set
QY_TEST_SET = QY[QY_TEST_SET_INDEX]
hopt_TEST_SET = hopt[hopt_TEST_SET_INDEX]
PCE_TEST_SET = PCE[PCE_TEST_SET_INDEX]

print(f'{QY_TEST_SET}\n{hopt_TEST_SET}\n{PCE_TEST_SET}')

# Replace the test set with zeros
QY[QY_TEST_SET_INDEX] = 0
hopt[hopt_TEST_SET_INDEX] = 0
PCE[PCE_TEST_SET_INDEX] = 0

print(f'{QY[QY_TEST_SET_INDEX]}\n{hopt[hopt_TEST_SET_INDEX]}\n{PCE[PCE_TEST_SET_INDEX]}')

[86.  25.  67.  53.   1.6 30.5 89.  89.5]
[1.85 0.02 0.28 2.95 0.7  1.2 ]
[2.25e+00 1.33e+00 4.71e-04 1.90e-03 8.00e-02]
[0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0.]


# Write on the X Matrix again
X.T[6] = QY
X.T[7] = hopt
X.T[8] = PCE


# Grid Search
ks = [2,3,4,5,6,7,8]
seeds = [53, 59, 61, 67, 71, 73, 79, 83, 89, 97]

# Store best solution (min cost)
min_cost = float('inf')
solution = None

for k in ks:
    for s in seeds:
        Xr, W, H, cost = nmf.nmf_mu(X, k=k, seed=s)
        if cost < min_cost:
            min_cost = cost
            solution = (k, s)


print(f"{cost} {solution}")

49.7770480742326 (8, 59)


# Measure the performance of the reconstruction
Xr, W, H, cost = nmf.nmf_mu(X, k=solution[0], seed=solution[1])

# Get the predicted QY, hopt and PCE
QY = Xr.T[6]
hopt = Xr.T[7]
PCE = Xr.T[8]

QY_PREDICT_SET = QY[QY_TEST_SET_INDEX]
hopt_PREDICT_SET = hopt[hopt_TEST_SET_INDEX]
PCE_PREDICT_SET = PCE[PCE_TEST_SET_INDEX]

print(f'{QY_PREDICT_SET}\n{hopt_PREDICT_SET}\n{PCE_PREDICT_SET}')

[15.97727897 62.32648612 90.01184508 19.35966872 59.88768401 72.13344412
 18.33772585 46.85491737]
[12.57010428  4.919815    1.98392266 24.25932488  2.95390967  1.06247509]
[1.83368088 0.07531809 0.58336117 0.60496385 0.67724153]


rmse_qy = math.sqrt(mean_squared_error(QY_TEST_SET, QY_PREDICT_SET))
rmse_hopt = math.sqrt(mean_squared_error(hopt_TEST_SET, hopt_PREDICT_SET))
rmse_PCE = math.sqrt(mean_squared_error(PCE_TEST_SET, PCE_PREDICT_SET))

print(f'RMSE(QY): {rmse_qy} ({QY_AVG} ± {QY_STD})')
print(f'RMSE(HOPT): {rmse_hopt} ({hopt_AVG} ± {hopt_STD})')
print(f'RMSE(PCE): {rmse_PCE} ({PCE_AVG} ± {PCE_STD})')

RMSE(QY): 49.875122512813185 (54.22035714285715 ± 26.58863969041543)
RMSE(HOPT): 10.008484102517194 (5.469478260869565 ± 8.892388483707826)
RMSE(PCE): 0.7493587531423203 (0.5521064117647059 ± 0.9382626018509556)


# Grid Search
ks = [2,3,4,5,6,7,8]
seeds = [53, 59, 61, 67, 71, 73, 79, 83, 89, 97]

# Store best solution (min cost)
min_cost = float('inf')
solution = None

for k in ks:
    for s in seeds:
        Xr, _, _, _ = nmf.nmf_mu(X, k=k, seed=s)
        # Get the values with the mask
        hopt = Xr.T[7]
        PCE = Xr.T[8]
        hopt_PREDICT_SET = hopt[hopt_TEST_SET_INDEX]
        PCE_PREDICT_SET = PCE[PCE_TEST_SET_INDEX]
        # Compute the cost of the test set
        rmse_hopt = math.sqrt(mean_squared_error(hopt_TEST_SET, hopt_PREDICT_SET))
        rmse_PCE = math.sqrt(mean_squared_error(PCE_TEST_SET, PCE_PREDICT_SET))
        #cost = rmse_hopt + rmse_PCE
        #cost = rmse_hopt
        cost = rmse_PCE
        if cost < min_cost:
            min_cost = cost
            solution = (k, s)


print(f"{cost} {solution}")

0.6433135652975813 (6, 83)


# Measure the performance of the reconstruction
Xr, W, H, cost = nmf.nmf_mu(X, k=solution[0], seed=solution[1])

# Get the predicted QY, hopt and PCE
QY = Xr.T[6]
hopt = Xr.T[7]
PCE = Xr.T[8]

QY_PREDICT_SET = QY[QY_TEST_SET_INDEX]
hopt_PREDICT_SET = hopt[hopt_TEST_SET_INDEX]
PCE_PREDICT_SET = PCE[PCE_TEST_SET_INDEX]

print(f'{QY_PREDICT_SET}\n{hopt_PREDICT_SET}\n{PCE_PREDICT_SET}')

[ 37.75873316  80.51076649  62.08184412 143.49604739  73.47495419
  43.23225725  94.97112549  94.22130926]
[11.68839014  5.07296792  4.07583527 19.44763593  5.26625266  4.70790051]
[1.9742166  2.1266637  0.3299664  0.51122061 0.54863358]


rmse_qy = math.sqrt(mean_squared_error(QY_TEST_SET, QY_PREDICT_SET))
rmse_hopt = math.sqrt(mean_squared_error(hopt_TEST_SET, hopt_PREDICT_SET))
rmse_PCE = math.sqrt(mean_squared_error(PCE_TEST_SET, PCE_PREDICT_SET))

print(f'RMSE(QY): {rmse_qy} ({QY_AVG} ± {QY_STD})')
print(f'RMSE(HOPT): {rmse_hopt} ({hopt_AVG} ± {hopt_STD})')
print(f'RMSE(PCE): {rmse_PCE} ({PCE_AVG} ± {PCE_STD})')

RMSE(QY): 48.74481047927994 (54.22035714285715 ± 26.58863969041543)
RMSE(HOPT): 8.583538425748353 (5.469478260869565 ± 8.892388483707826)
RMSE(PCE): 0.5095726953252181 (0.5521064117647059 ± 0.9382626018509556)


# Get the original matrix
X = df[['abs_peak', 'abs_min', 'abs_max', 'em_peak', 'em_min', 'em_max', 'QY (%)', 'hopt (%)', 'PCE (%)']].to_numpy()
X[np.isnan(X)] = 0
print(X.shape)

# Get the reconstructed matrix
Xr, _, _, _ = nmf.nmf_mu(X, k=solution[0], seed=solution[1])

# Replace all zeros with reconstructed values
X[X==0] = Xr[X==0]

(28, 9)

X

array([[3.70000000e+02, 3.00000000e+02, 4.50000000e+02, 6.50000000e+02,
        4.50000000e+02, 7.50000000e+02, 6.70000000e+01, 5.50000000e+00,
        1.30557497e+00],
       [3.75000000e+02, 3.00000000e+02, 4.50000000e+02, 7.50000000e+02,
        4.00000000e+02, 9.00000000e+02, 4.50000000e+01, 4.25000000e+00,
        1.33000000e+00],
       [4.80000000e+02, 3.00000000e+02, 5.00000000e+02, 6.19000000e+02,
        5.70000000e+02, 6.70000000e+02, 3.62000000e+01, 2.95000000e+00,
        2.25000000e+00],
       [4.00000000e+02, 3.00000000e+02, 5.00000000e+02, 6.00000000e+02,
        5.00000000e+02, 7.00000000e+02, 2.50000000e+01, 1.85000000e+00,
        1.78174879e+00],
       [4.46000000e+02, 2.50000000e+02, 5.00000000e+02, 5.53000000e+02,
        5.00000000e+02, 8.00000000e+02, 8.95000000e+01, 3.13000000e+01,
        1.14920925e+00],
       [4.49000000e+02, 2.50000000e+02, 5.50000000e+02, 5.71000000e+02,
        5.00000000e+02, 8.00000000e+02, 8.00000000e+01, 2.78000000e+01,
        1.69867716e+00],
       [4.91000000e+02, 3.00000000e+02, 5.00000000e+02, 5.81000000e+02,
        5.50000000e+02, 6.50000000e+02, 9.50000000e+01, 2.37000000e+01,
        2.81000000e+00],
       [3.80000000e+02, 2.50000000e+02, 4.00000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.10000000e+02, 3.05000000e+01, 3.40000000e-01,
        1.90000000e-03],
       [3.60000000e+02, 2.50000000e+02, 3.80000000e+02, 5.45000000e+02,
        4.50000000e+02, 7.00000000e+02, 1.60000000e+00, 2.70000000e-01,
        7.80000000e-04],
       [3.70000000e+02, 2.90000000e+02, 3.80000000e+02, 6.11000000e+02,
        5.70000000e+02, 7.10000000e+02, 2.70000000e+01, 3.20000000e+00,
        7.00000000e-03],
       [3.50000000e+02, 2.40000000e+02, 4.20000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.10000000e+02, 3.40000000e+01, 4.30000000e+00,
        8.43871139e-01],
       [3.25000000e+02, 2.40000000e+02, 4.00000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.10000000e+02, 8.00000000e+00, 1.20000000e+00,
        8.08810112e-01],
       [3.70000000e+02, 2.40000000e+02, 4.00000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.10000000e+02, 6.30000000e+01, 9.00000000e+00,
        4.13560588e-01],
       [3.70000000e+02, 3.00000000e+02, 3.80000000e+02, 6.15000000e+02,
        5.70000000e+02, 7.10000000e+02, 6.10000000e+01, 1.20000000e+00,
        2.00000000e-01],
       [3.80000000e+02, 2.40000000e+02, 3.80000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.10000000e+02, 2.30000000e+01, 4.30000000e-01,
        3.00000000e-02],
       [3.60000000e+02, 2.40000000e+02, 3.80000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.10000000e+02, 3.00000000e+01, 1.00000000e-02,
        6.00000000e-04],
       [3.60000000e+02, 2.40000000e+02, 4.20000000e+02, 6.15000000e+02,
        5.70000000e+02, 7.10000000e+02, 8.50000000e+01, 2.30000000e+00,
        8.60000000e-04],
       [3.40000000e+02, 2.50000000e+02, 3.80000000e+02, 6.13000000e+02,
        5.70000000e+02, 7.10000000e+02, 4.40000000e+01, 4.95152985e+00,
        4.41000000e-02],
       [4.05000000e+02, 2.50000000e+02, 4.20000000e+02, 6.13000000e+02,
        5.70000000e+02, 7.10000000e+02, 4.40000000e+01, 5.16163221e+00,
        4.99000000e-02],
       [3.50000000e+02, 2.50000000e+02, 4.00000000e+02, 6.13000000e+02,
        5.70000000e+02, 7.10000000e+02, 7.30000000e+01, 2.80000000e-01,
        2.80000000e-01],
       [3.20000000e+02, 2.50000000e+02, 3.50000000e+02, 6.13000000e+02,
        5.70000000e+02, 7.10000000e+02, 8.60000000e+01, 6.49216118e+00,
        1.22326850e-01],
       [3.70000000e+02, 3.00000000e+02, 4.50000000e+02, 6.15000000e+02,
        5.70000000e+02, 7.10000000e+02, 8.90000000e+01, 7.00000000e-01,
        6.61502043e-01],
       [3.70000000e+02, 3.00000000e+02, 4.50000000e+02, 6.15000000e+02,
        5.70000000e+02, 7.10000000e+02, 8.90000000e+01, 9.63044260e+00,
        8.00000000e-02],
       [3.96000000e+02, 3.50000000e+02, 4.50000000e+02, 5.82000000e+02,
        5.00000000e+02, 7.00000000e+02, 5.30000000e+01, 8.78474482e+00,
        1.08010617e+00],
       [3.20000000e+02, 3.00000000e+02, 5.50000000e+02, 6.70000000e+02,
        6.00000000e+02, 7.00000000e+02, 3.29700000e+01, 2.55000000e+00,
        1.99733817e+00],
       [4.04000000e+02, 3.00000000e+02, 5.50000000e+02, 5.94000000e+02,
        5.00000000e+02, 7.50000000e+02, 8.64000000e+01, 2.60000000e+00,
        2.30000000e+00],
       [3.70000000e+02, 2.50000000e+02, 4.00000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.20000000e+02, 6.00000000e+01, 2.00000000e-02,
        1.98000000e-04],
       [3.70000000e+02, 2.50000000e+02, 4.00000000e+02, 6.12000000e+02,
        5.70000000e+02, 7.20000000e+02, 6.00000000e+01, 4.80000000e-02,
        4.71000000e-04]])


Xr, W, H, cost = nmf.nmf_mu(X, k=solution[0], seed=solution[1])
_, cols = X.shape
field_names = df.columns
print(f'{field_names}')
df = pl.DataFrame({field_names[i+2]: X[:,i] for i in range(cols)})
df

['#', 'mat0', 'mat1', 'abs_peak', 'abs_min', 'abs_max', 'em_peak', 'em_min', 'em_max', 'QY (%)', 'hopt (%)', 'PCE (%)']

mat1	abs_peak	abs_min	abs_max	em_peak	em_min	em_max	QY (%)	hopt (%)
f64	f64	f64	f64	f64	f64	f64	f64	f64
370.0	300.0	450.0	650.0	450.0	750.0	67.0	5.5	1.305575
375.0	300.0	450.0	750.0	400.0	900.0	45.0	4.25	1.33
480.0	300.0	500.0	619.0	570.0	670.0	36.2	2.95	2.25
400.0	300.0	500.0	600.0	500.0	700.0	25.0	1.85	1.781749
446.0	250.0	500.0	553.0	500.0	800.0	89.5	31.3	1.149209
449.0	250.0	550.0	571.0	500.0	800.0	80.0	27.8	1.698677
491.0	300.0	500.0	581.0	550.0	650.0	95.0	23.7	2.81
380.0	250.0	400.0	612.0	570.0	710.0	30.5	0.34	0.0019
360.0	250.0	380.0	545.0	450.0	700.0	1.6	0.27	0.00078
370.0	290.0	380.0	611.0	570.0	710.0	27.0	3.2	0.007
350.0	240.0	420.0	612.0	570.0	710.0	34.0	4.3	0.843871
325.0	240.0	400.0	612.0	570.0	710.0	8.0	1.2	0.80881
370.0	240.0	400.0	612.0	570.0	710.0	63.0	9.0	0.413561
370.0	300.0	380.0	615.0	570.0	710.0	61.0	1.2	0.2
380.0	240.0	380.0	612.0	570.0	710.0	23.0	0.43	0.03
360.0	240.0	380.0	612.0	570.0	710.0	30.0	0.01	0.0006
360.0	240.0	420.0	615.0	570.0	710.0	85.0	2.3	0.00086
340.0	250.0	380.0	613.0	570.0	710.0	44.0	4.95153	0.0441
405.0	250.0	420.0	613.0	570.0	710.0	44.0	5.161632	0.0499
350.0	250.0	400.0	613.0	570.0	710.0	73.0	0.28	0.28
320.0	250.0	350.0	613.0	570.0	710.0	86.0	6.492161	0.122327
370.0	300.0	450.0	615.0	570.0	710.0	89.0	0.7	0.661502
370.0	300.0	450.0	615.0	570.0	710.0	89.0	9.630443	0.08
396.0	350.0	450.0	582.0	500.0	700.0	53.0	8.784745	1.080106
320.0	300.0	550.0	670.0	600.0	700.0	32.97	2.55	1.997338
404.0	300.0	550.0	594.0	500.0	750.0	86.4	2.6	2.3
370.0	250.0	400.0	612.0	570.0	720.0	60.0	0.02	0.000198
370.0	250.0	400.0	612.0	570.0	720.0	60.0	0.048	0.000471

Sunlight Harvesting Energy Conversion¶

Dataset visualization and analysis¶

PCE and hopt prediction¶

Baseline (using only abs and em)¶

Baseline + QY¶

Baseline + QY + Categorical (Mat0 and Mat1)¶

Outlier removal¶

PCE and hopt baselines¶

Baseline + QY¶

Baseline + QY + Categorical (Mat0 and Mat1)¶

Clustering¶

Previous version¶

Grid Search (optimize with test set)¶

Reconstruct the matrix¶

mat0	mat1	abs_peak	abs_min	abs_max	em_peak	em_min	em_max	QY (%)	hopt (%)	PCE (%)
str	str	i64	i64	i64	i64	i64	i64	f64	f64	f64
"dye"	"film"	578	420	600	613	550	750	98.0	18.8	null
"dye"	"bulk"	540	400	600	590	540	690	null	null	null
"dye"	"bulk"	540	400	600	590	540	690	null	null	null
"QD"	"bulk"	730	600	900	910	800	1000	null	2.5	null
"QD"	"bulk"	730	600	900	910	800	1000	null	2.5	null
"QD"	"fiber"	730	600	900	910	800	1000	null	4.0	null
"QD"	"fiber"	730	600	900	910	800	1000	null	7.0	null
"QD"	"solution"	800	400	800	900	700	1000	30.0	1.4	3.2
"QD"	"solution"	600	400	600	630	600	700	50.0	0.5	1.2
"dye"	"solution"	550	450	600	580	550	650	null	null	1.3
"QD"	"solution"	376	300	650	623	600	700	50.0	0.3	null
"dye"	"solution"	413	400	600	657	600	800	67.0	3.4	null
"dye"	"solution"	550	450	600	629	550	750	95.0	2.6	null
"dye"	"solution"	466	300	750	685	700	900	11.0	0.6	null
"dye"	"solution"	557	300	750	802	700	900	9.0	0.5	null
"polymer"	"solution"	460	350	550	592	550	800	45.0	1.0	null
"polymer"	"solution"	467	300	550	593	550	700	48.0	0.9	null
"dye"	"film"	403	300	450	471	400	600	40.8	7.7	null
"dye"	"bulk"	374	300	400	450	400	600	100.0	null	null
"dye"	"bulk"	370	300	450	650	450	750	67.0	5.5	null
"NP"	"bulk"	470	400	550	597	500	725	null	4.09	3.55
"dye"	"bulk"	620	400	600	653	600	800	null	null	0.55
"dye"	"bulk"	340	300	400	540	400	700	14.0	0.25	null
"dye"	"bulk"	340	300	400	480	400	600	78.0	0.4	null
"dye"	"bulk"	580	300	600	620	600	800	100.0	null	0.0018
"dye"	"film"	745	400	850	808	700	900	25.0	null	0.61
"dye"	"film"	745	400	900	808	700	900	25.0	null	1.24
"dye"	"film"	745	400	850	808	700	900	25.0	null	0.54
"dye"	"film"	745	400	900	808	700	900	25.0	null	1.41
"dye"	"bulk"	525	400	650	610	500	800	97.6	null	2.6
"NP"	"bulk"	375	300	450	750	400	900	45.0	4.25	1.33
"Lndye"	"fiber"	540	350	550	630	500	700	null	0.29	null
"dye"	"bulk"	380	300	500	509	480	700	null	10.4	2.2
"NP"	"bulk"	550	400	750	800	600	1000	80.0	6.8	null
"QD"	"film"	450	370	600	630	600	700	null	null	null
"QD"	"film"	450	400	600	830	650	975	40.0	null	null
"QD"	"waveguide"	650	500	770	718	520	850	63.0	1.75	null
"QD"	"solution"	650	500	770	718	520	850	63.0	3.67	null
"QD"	"film"	480	300	500	619	570	670	36.2	2.95	2.25
"CD"	"bulk"	350	300	400	435	380	575	null	12.23	2.63
"CD"	"bulk"	350	280	400	450	390	600	null	4.52	2.49
"CD"	"film"	350	300	425	510	400	650	45.0	12.0	null
"CD"	"film"	358	225	425	441	400	600	94.0	3.9	null
"CD"	"film"	325	300	400	430	380	600	null	5.02	4.97
"CD"	"bulk"	340	300	600	540	450	700	40.0	0.92	null
"CDQD"	"tandem"	450	300	550	620	450	700	45.0	1.4	null
"CDdye"	"bulk"	470	350	550	560	380	750	null	null	4.06
"CDQD"	"bulk"	400	300	500	500	400	550	70.0	null	3.05
"NP"	"film"	400	300	500	600	500	700	25.0	1.85	null
"NP"	"film"	500	400	600	532	480	600	92.0	null	null
"NP"	"bulk"	325	300	520	518	475	525	58.0	2.4	1.8
"CD"	"film"	380	280	700	420	400	650	null	4.75	3.94
"CD"	"bulk"	440	300	500	540	450	700	25.0	1.2	null
"QD"	"bulk"	500	400	600	830	600	1000	50.0	null	2.85
"QD"	"bulk"	500	350	750	627	550	700	35.9	1.45	null
"QD"	"film"	450	350	750	862	800	1100	91.0	8.1	2.94
"QD"	"bulk"	350	300	500	550	450	775	81.0	26.5	8.71
"QD"	"bulk"	350	300	500	588	450	750	null	null	4.2
"QD"	"film"	350	400	800	740	600	850	null	6.97	3.18
"QD"	"bulk"	500	350	650	805	600	1000	78.0	6.4	3.1
"QD"	"bulk"	640	400	1000	960	700	1200	40.0	null	3.27
"QD"	"bulk"	415	310	620	918	620	1240	60.3	null	3.94
"QD"	"bulk"	375	300	500	638	500	825	null	null	null
"QD"	"bulk"	360	325	500	600	475	700	53.0	null	null
"Ln"	"bulk"	650	400	900	1140	1000	1200	null	null	null
"dye"	"bulk"	446	250	500	553	500	800	89.5	31.3	null
"dye"	"bulk"	478	250	600	601	550	800	61.1	22.0	null
"dye"	"bulk"	513	300	650	642	650	800	24.8	3.3	null
"dye"	"bulk"	449	250	550	571	500	800	80.0	27.8	null
"dye"	"bulk"	473	250	600	607	500	800	44.3	24.7	null
"dye"	"film"	760	600	800	787	700	900	24.0	null	0.44
"dye"	"film"	760	600	800	787	700	900	24.0	null	0.28
"dye"	"film"	700	550	800	784	700	900	30.0	null	0.62
"dye"	"film"	700	550	800	784	700	900	30.0	null	0.36
"dye"	"film"	738	550	850	819	700	900	23.0	null	0.41
"dye"	"film"	738	550	850	819	700	900	23.0	null	0.28
"QD"	"bulk"	450	350	1000	825	650	1000	null	null	7.9
"QD"	"bulk"	763	350	950	856	650	1050	70.0	null	4.74
"dye"	"bulk"	491	300	500	581	550	650	95.0	23.7	2.81
"dye"	"bulk"	580	350	600	620	400	800	null	null	7.1
"dye"	"bulk"	450	300	350	480	450	600	17.0	null	8.99
"Ln"	"bulk"	347	250	400	613	570	710	null	2.47	0.19
"Ln"	"bulk"	590	280	600	630	550	700	65.0	null	11.3
"Ln"	"film"	380	250	400	612	570	710	30.5	0.34	0.0019
"Ln"	"film"	360	250	380	545	450	700	1.6	0.27	0.00078
"Ln"	"film"	370	290	380	611	570	710	27.0	3.2	0.007
"Ln"	"film"	290	280	400	546	380	650	40.0	8.8	null
"Ln"	"film"	350	240	420	612	570	710	34.0	4.3	null
"Ln"	"film"	325	240	400	612	570	710	8.0	1.2	null
"Ln"	"film"	325	240	400	544	450	650	12.0	1.7	null
"Ln"	"film"	290	200	380	610	570	710	null	null	null
"Ln"	"film"	370	240	400	612	570	710	63.0	9.0	null
"Ln"	"film"	370	300	380	615	570	710	61.0	1.2	0.2
"Ln"	"film"	380	240	380	612	570	710	23.0	0.43	0.03
"Ln"	"film"	360	240	380	612	570	710	30.0	0.01	0.0006
"Ln"	"fiber"	360	240	420	615	570	710	85.0	2.3	0.00086
"dye"	"film"	520	300	540	590	550	700	78.0	0.08	null
"dye"	"fiber"	520	300	540	590	550	700	78.0	1.6	0.0052
"dye"	"fiber"	520	300	540	590	550	700	93.0	8.0	0.0024
"Ln"	"film"	340	250	380	613	570	710	44.0	null	0.0441
"Ln"	"film"	405	250	420	613	570	710	44.0	null	0.0499
"Ln"	"film"	350	250	400	613	570	710	73.0	0.28	0.28
"Ln"	"film"	320	250	350	613	570	710	86.0	null	null
"dye"	"bulk"	570	300	600	650	350	750	80.0	14.5	2.16
"dye"	"film"	770	300	800	775	700	950	16.0	1.5	null
"dye"	"bulk"	665	250	700	670	600	750	12.0	3.7	0.1
"Ln"	"fiber"	370	300	450	615	570	710	89.0	0.7	null
"dye"	"fiber"	560	300	600	580	550	700	95.0	2.1	null
"dye"	"fiber"	780	300	750	730	650	850	21.0	0.5	null
"Ln"	"fiber"	370	300	450	615	570	710	89.0	null	0.08
"dye"	"fiber"	560	300	600	580	550	700	95.0	null	0.21
"QD"	"bulk"	580	500	620	630	590	700	10.0	null	2.1
"QD"	"bulk"	580	500	620	630	590	700	60.0	null	2.1
"dye"	"bulk"	575	400	610	620	570	720	95.0	null	3.3
"QD"	"bulk"	580	500	620	630	590	700	10.0	null	2.1
"QD"	"bulk"	450	400	650	634	580	680	44.0	null	2.8
"QD"	"bulk"	450	400	600	580	550	650	86.0	48.0	null
"dye"	"film"	570	300	700	600	350	700	null	null	null
"QD"	"film"	396	350	450	582	500	700	53.0	null	null
"Ln"	"bulk"	530	300	580	630	550	750	83.0	null	1.44
"QD"	"bulk"	473	350	550	640	600	700	45.0	1.0	null
"QD"	"bulk"	350	300	450	550	450	750	56.0	null	8.71
"QD"	"bulk"	470	400	600	550	450	700	20.0	2.01	null
"dye"	"bulk"	521	450	550	539	500	700	93.0	54.0	null
"CD"	"film"	450	310	510	525	500	700	11.0	7.58	6.0
"dye"	"film"	545	400	700	680	550	800	50.0	12.5	null
"dye"	"solution"	498	300	700	580	520	700	30.0	6.88	0.27
"dye"	"solution"	569	350	600	595	550	750	61.0	2.58	null
"dye"	"solution"	488	300	500	510	450	600	51.0	3.3	0.35
"CD"	"bulk"	460	350	500	510	350	500	54.0	2.7	null
"CD"	"bulk"	340	300	500	520	400	700	6.0	5.84	null
"CD"	"bulk"	720	250	800	490	400	600	65.0	null	8.75
"CD"	"film"	420	300	550	515	400	700	40.0	1.6	0.7
"CD"	"film"	557	300	600	612	400	700	70.0	2.3	null
"CD"	"film"	420	300	550	500	440	600	67.0	2.2	1.13
"dye"	"bulk"	575	400	610	620	570	700	96.0	37.7	null
"CD"	"solution"	491	250	520	520	500	700	82.0	5.43	0.18
"CD"	"film"	510	250	520	535	400	650	78.0	0.058	0.00083
"CD"	"film"	510	250	520	535	400	650	78.0	1.7	0.014
"dye"	"bulk"	575	400	610	620	570	720	95.0	19.0	2.9
"QD"	"bulk"	480	400	660	622	550	700	15.7	3.2	0.62
"CD"	"film"	405	300	500	520	400	700	70.0	3.2	1.9
"CD"	"film"	405	300	500	520	400	700	65.0	2.9	1.7
"QDdye"	"bulk"	500	400	700	600	450	750	32.7	1.0	null
"CD"	"film"	347	280	500	540	450	700	61.0	4.56	4.1
"Ln"	"bulk"	405	250	500	520	450	700	81.0	3.4	1.37
"CD"	"film"	490	300	520	510	450	650	80.5	null	2.06
"CD"	"film"	490	300	520	510	450	650	80.5	4.8	4.36
"CD"	"film"	380	300	450	450	400	700	11.54	1.36	null
"QD"	"film"	300	300	550	515	450	550	35.91	3.08	null
"QD"	"film"	320	300	550	670	600	700	32.97	2.55	null
"CDQD"	"film"	320	300	550	515	400	700	23.0	1.89	null
"CDQD"	"film"	320	300	550	670	400	700	22.0	2.54	null
"CDQD"	"film"	320	300	550	500	400	700	26.0	3.76	null
"CD"	"film"	350	300	650	580	450	750	35.0	null	1.9
"CD"	"film"	380	300	500	520	400	700	35.0	null	1.7
"CD"	"film"	370	300	650	560	400	775	35.0	null	2.3
"CD"	"film"	400	300	500	517	450	700	33.0	4.5	0.117
"CD"	"bulk"	400	300	500	517	450	700	41.0	5.89	0.16
"CD"	"bulk"	400	300	500	517	450	700	41.0	3.13	0.061
"CD"	"film"	404	300	550	594	500	750	86.4	2.6	2.3
"CD"	"film"	555	300	650	650	575	800	17.6	3.0	2.7
"CD"	"film"	450	300	660	600	500	800	60.0	4.3	3.8
"CD"	"solution"	340	300	450	520	400	700	null	1.23	0.43
"CD"	"film"	340	300	450	520	400	700	null	0.9	0.62
"CD"	"bulk"	470	300	550	535	450	650	9.6	9.3	null
"CD"	"film"	380	300	500	570	450	700	41.52	3.51	2.39
"CD"	"film"	355	300	500	520	450	650	15.01	2.76	1.94
"CD"	"film"	410	300	600	608	550	750	7.6	2.77	1.96
"CD"	"film"	400	300	600	600	450	750	22.0	4.03	2.92
"QD"	"bulk"	600	400	650	625	550	700	30.0	2.7	0.38
"QD"	"bulk"	350	300	500	495	425	700	91.0	null	4.29
"QD"	"bulk"	350	300	500	495	425	700	91.0	null	0.55
"QD"	"bulk"	350	300	500	578	450	700	11.0	null	0.77
"Ln"	"film"	450	385	250	615	720	570	44.0	4.8	0.054
"Ln"	"film"	400	275	250	543	700	470	37.0	7.7	0.058
"CD"	"film"	425	340	250	425	600	400	11.0	13.1	0.053
"Ln"	"film"	450	385	250	615	720	570	44.0	5.2	0.046
"Ln"	"film"	400	275	250	543	700	470	37.0	7.7	0.047
"CD"	"film"	425	340	250	425	600	400	11.0	12.8	0.041
"Ln"	"film"	450	390	250	612	720	570	59.0	6.7	0.074
"Ln"	"film"	400	280	250	543	700	470	54.0	8.5	0.065
"Ln"	"film"	450	390	250	612	720	570	59.0	10.7	0.096
"Ln"	"film"	400	280	250	543	700	470	54.0	8.7	0.053
"Ln"	"film"	450	390	250	612	720	570	59.0	11.7	0.142
"Ln"	"film"	400	280	250	543	700	470	54.0	16.5	0.136
"dye"	"film"	650	415	250	690	900	600	4.0	2.6	0.044
"polymer"	"film"	500	392	250	491	650	400	47.0	5.71	2.29
"polymer"	"film"	500	392	250	473	650	450	57.0	9.112	2.32
"polymer"	"film"	500	392	250	454	650	400	68.0	12.08	2.47
"polymer"	"film"	500	392	250	491	650	400	47.0	5.71	4.38
"polymer"	"film"	500	392	250	473	650	450	57.0	9.112	4.62
"polymer"	"film"	500	392	250	454	650	400	68.0	12.08	4.92
"NP"	"bulk"	600	511	450	527	580	490	65.0	0.15	0.049413
"dye"	"bulk"	600	554	450	612	700	575	70.0	0.16	0.050786
"NPdye"	"bulk"	600	530	450	550	700	500	68.0	0.22	0.07531
"QD"	"solution"	510	450	300	517	550	475	89.0	2.32	0.020944
"dye"	"solution"	660	480	680	665	600	800	31.0	2.65	0.21
"Ln"	"film"	370	250	400	612	570	720	60.0	0.02	0.000198
"CD"	"film"	510	250	520	535	400	650	78.0	0.035	0.000182
"Ln"	"film"	370	250	400	612	570	720	60.0	0.048	0.000471